15M steps

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b6d608c4248e0b310070b2af2b4ea2275b174aeed4ae07c4b7ff7524ee580d5
+oid sha256:78d80a03b6c3ffa7be5d4037e3815a3696b1e1198da3bea1d6bcfc61028f6587
 size 895526

SoccerTwos/SoccerTwos-13499994.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ad54bea8430cb2786318de3ce8dde082b5f65d22499ece282e7c51cad5dfdad
+size 895526

SoccerTwos/SoccerTwos-13499994.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:984e380fa477b8269f25a1e5f34519a210f75d9ce207300e85a586c3bedefbc8
+size 10325290

SoccerTwos/SoccerTwos-13999986.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cf6c9eb6e522f7d25eb7e5e92d7c331bea382d26bbf1980680217d2161c6257
+size 895526

SoccerTwos/SoccerTwos-13999986.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28b465cf20ff188aec6de3d33e14b17ed46e2af4cee6410df185c96dfe51df34
+size 10325290

SoccerTwos/SoccerTwos-14499998.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e48ad434cf6c13fe55dfe514fb5c912e928dafcd12fb78ebcce137c40e0610f9
+size 895526

SoccerTwos/SoccerTwos-14499998.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7a40b1cf22bd1c8975c79ebf98fb6728392a5c082ebb0c4325bcab83ecf9ed7
+size 10325290

SoccerTwos/SoccerTwos-14999982.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:387813bafb9dfb3244a8e0b084dd2b2b21f2fe6895e52b6f93247fa389f90105
+size 895526

SoccerTwos/SoccerTwos-14999982.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcc979094443202bf62830d19a8f572eb192a0dcb0b65502c8f1a3c6b2c29cf8
+size 10325290

SoccerTwos/SoccerTwos-15000014.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78d80a03b6c3ffa7be5d4037e3815a3696b1e1198da3bea1d6bcfc61028f6587
+size 895526

SoccerTwos/SoccerTwos-15000014.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aae125a758c60aebaea95e62b8c64d403e394391f33d5fe49424f886618188f6
+size 10325290

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37854fa1cf62607fbcf6e1fa3522fdc3890a2084987edc894f3955253d66549d
+oid sha256:55c392f23767ea885f166609ad60d396536d6c5888529ce286af22bccd997bd9
 size 10323922

SoccerTwos/events.out.tfevents.1710358561.stephan-ms7c02.36177.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:792f7edae81403905fc5199882d2424fca8d5b5a21404635a88621361bf9c398
+size 1319

SoccerTwos/events.out.tfevents.1710358577.stephan-ms7c02.36326.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d76291da51fd3588d0e00aa3006735bc784ceabafc32923690126f5c039b7957
+size 5082615

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 4096, "buffer_size": 65536, "learning_rate": 0.0004345843188705317, "beta": 0.00019215097636640332, "epsilon": 0.15831928707038231, "lambd": 0.9467147291117369, "num_epoch": 5, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": true, "hidden_units": 256, "num_layers": 3, "vis_encode_type": "fully_connected", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.9608227414353802, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 10000000, "time_horizon": 32, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 60000, "team_change": 589998, "swap_steps": 70000, "window": 25, "play_against_latest_model_ratio": 0.75, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./ml-agents/training-envs-executables/SoccerTwos.exe", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 1280, "height": 720, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": false, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos-read-deal", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 4096, "buffer_size": 65536, "learning_rate": 0.0004345843188705317, "beta": 0.00019215097636640332, "epsilon": 0.15831928707038231, "lambd": 0.9467147291117369, "num_epoch": 5, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": true, "hidden_units": 256, "num_layers": 3, "vis_encode_type": "fully_connected", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.9608227414353802, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 15000000, "time_horizon": 32, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 60000, "team_change": 589998, "swap_steps": 70000, "window": 25, "play_against_latest_model_ratio": 0.75, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./ml-agents/training-envs-executables/SoccerTwos.exe", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 1280, "height": 720, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": false, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos-read-deal", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -37,7 +37,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 10000000
+    max_steps: 15000000
     time_horizon: 32
     summary_freq: 10000
     threaded: false

run_logs/Player-0.log

@@ -19,14 +19,14 @@ ns GL_ARB_stencil_texturing GL_ARB_sync GL_ARB_tessellation_shader GL_ARB_textur
 _buffer_object GL_ARB_vertex_shader GL_ARB_vertex_type_10f_11f_11f_rev GL_ARB_vertex_type_2_10_10_10_rev GL_ARB_viewport_array GL_ATI_blend_equation_separate GL_ATI_meminfo GL_ATI_texture_float GL_ATI_texture_mirror_once GL_EXT_EGL_image_storage GL_EXT_EGL_sync GL_EXT_abgr GL_EXT_blend_equation_separate GL_EXT_debug_label GL_EXT_demote_to_helper_invocation GL_EXT_depth_bounds_test GL_EXT_draw_buffers2 GL_EXT_draw_instanced GL_EXT_framebuffer_blit GL_EXT_framebuffer_multisample GL_EXT_framebuffer_multisample_blit_scaled GL_EXT_framebuffer_object GL_EXT_framebuffer_sRGB GL_EXT_memory_object GL_EXT_memory_object_fd GL_EXT_packed_depth_stencil GL_EXT_packed_float GL_EXT_pixel_buffer_object GL_EXT_polygon_offset_clamp GL_EXT_provoking_vertex GL_EXT_semaphore GL_EXT_semaphore_fd GL_EXT_shader_image_load_formatted GL_EXT_shader_image_load_store GL_EXT_shader_integer_mix GL_EXT_shader_samples_identical GL_EXT_texture_array GL_EXT_texture_compression_dxt1 GL_EXT_texture_compression_rgtc GL_EXT_texture_compression_s3t
 c GL_EXT_texture_filter_anisotropic GL_EXT_texture_integer GL_EXT_texture_mirror_clamp GL_EXT_texture_sRGB GL_EXT_texture_sRGB_R8 GL_EXT_texture_sRGB_decode GL_EXT_texture_shadow_lod GL_EXT_texture_shared_exponent GL_EXT_texture_snorm GL_EXT_texture_swizzle GL_EXT_timer_query GL_EXT_transform_feedback GL_EXT_vertex_array_bgra GL_EXT_vertex_attrib_64bit GL_EXT_window_rectangles GL_IBM_multimode_draw_arrays GL_INTEL_blackhole_render GL_KHR_blend_equation_advanced GL_KHR_context_flush_control GL_KHR_debug GL_KHR_no_error GL_KHR_parallel_shader_compile GL_KHR_robust_buffer_access_behavior GL_KHR_robustness GL_KHR_texture_compression_astc_ldr GL_KHR_texture_compression_astc_sliced_3d GL_MESA_framebuffer_flip_y GL_MESA_pack_invert GL_MESA_shader_integer_functions GL_MESA_texture_const_bandwidth GL_MESA_texture_signed_rgba GL_NVX_gpu_memory_info GL_NV_alpha_to_coverage_dither_control GL_NV_compute_shader_derivatives GL_NV_conditional_render GL_NV_copy_image GL_NV_depth_clamp GL_NV_packed_depth_stencil GL_NV_shader_
 atomic_int64 GL_NV_texture_barrier GL_NV_vdpau_interop GL_OES_EGL_image GL_S3_s3tc
-OPENGL LOG: Creating OpenGL 4.6 graphics device ; Context level  <OpenGL 4.5> ; Context handle 22053744
+OPENGL LOG: Creating OpenGL 4.6 graphics device ; Context level  <OpenGL 4.5> ; Context handle 28321776
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.092 seconds
+- Completed reload, in  0.091 seconds
 Default vsync count 1
 requesting resize 1280 x 720
 resizing window to 1280 x 720
 Desktop is 1920 x 1080 @ 60 Hz
-UnloadTime: 0.807040 ms
+UnloadTime: 0.942291 ms
 Registered Communicator in Agent.
 Setting up 6 worker threads for Enlighten.
 requesting resize 1280 x 720
@@ -36,7 +36,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 62727 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 93732 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.1 MB
@@ -213,16 +213,16 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.9 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 62728 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 93733 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 13.0 MB
+      Peak Allocated memory 12.9 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 62728 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 93733 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 28.7 MB
+      Peak Allocated memory 28.8 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -251,13 +251,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.9 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 62727 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 93732 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 2.7 MB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [128.0 KB-256.0 KB]: 62728 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 93733 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 174.7 KB
@@ -269,13 +269,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.9 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 62727 frames, [1.0 MB-2.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 93732 frames, [1.0 MB-2.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 1.2 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 62728 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 93733 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 7.8 MB
@@ -287,13 +287,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.9 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 62728 frames
+      Peak usage frame count: [0-1.0 KB]: 93733 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 62727 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 93732 frames, [2.0 KB-4.0 KB]: 1 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 KB

run_logs/timers.json

@@ -2,201 +2,201 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 1.4048619270324707,
-            "min": 1.3750499486923218,
-            "max": 1.7051565647125244,
-            "count": 335
+            "value": 1.11602783203125,
+            "min": 1.1030526161193848,
+            "max": 1.4285537004470825,
+            "count": 500
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 28277.060546875,
-            "min": 14701.9814453125,
-            "max": 34322.671875,
-            "count": 335
+            "value": 22320.556640625,
+            "min": 21029.970703125,
+            "max": 28662.501953125,
+            "count": 500
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 45.06422018348624,
-            "min": 35.125,
-            "max": 53.40425531914894,
-            "count": 335
+            "value": 45.905660377358494,
+            "min": 35.28,
+            "max": 55.38202247191011,
+            "count": 500
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19648.0,
-            "min": 8072.0,
-            "max": 20960.0,
-            "count": 335
+            "value": 19464.0,
+            "min": 14112.0,
+            "max": 21312.0,
+            "count": 500
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1607.9046472284606,
-            "min": 1555.6832652825399,
-            "max": 1613.038356436412,
-            "count": 335
+            "value": 1672.5986965358836,
+            "min": 1594.9761687604023,
+            "max": 1684.8696129621046,
+            "count": 500
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 350523.2130958044,
-            "min": 163654.2453609866,
-            "max": 434134.2547516843,
-            "count": 335
+            "value": 354590.92366560735,
+            "min": 291606.7260394614,
+            "max": 450906.7595913422,
+            "count": 500
         },
         "SoccerTwos.Step.mean": {
-            "value": 9999982.0,
-            "min": 6659988.0,
-            "max": 9999982.0,
-            "count": 335
+            "value": 14999982.0,
+            "min": 10009972.0,
+            "max": 14999982.0,
+            "count": 500
         },
         "SoccerTwos.Step.sum": {
-            "value": 9999982.0,
-            "min": 6659988.0,
-            "max": 9999982.0,
-            "count": 335
+            "value": 14999982.0,
+            "min": 10009972.0,
+            "max": 14999982.0,
+            "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": 0.03223046660423279,
-            "min": -0.11106479167938232,
-            "max": 0.10332842171192169,
-            "count": 335
+            "value": -0.033846165984869,
+            "min": -0.10714015364646912,
+            "max": 0.09757562726736069,
+            "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": 13.246722221374512,
-            "min": -46.31401824951172,
-            "max": 44.017906188964844,
-            "count": 335
+            "value": -13.876928329467773,
+            "min": -45.2131462097168,
+            "max": 41.95751953125,
+            "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.031953852623701096,
-            "min": -0.11250180751085281,
-            "max": 0.10477326810359955,
-            "count": 335
+            "value": -0.03533671796321869,
+            "min": -0.11142526566982269,
+            "max": 0.10013997554779053,
+            "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 13.133033752441406,
-            "min": -46.91325378417969,
-            "max": 44.6334114074707,
-            "count": 335
+            "value": -14.488054275512695,
+            "min": -47.021461486816406,
+            "max": 43.06018829345703,
+            "count": 500
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 335
+            "count": 500
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 335
+            "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": 0.09531192604554903,
-            "min": -0.381275439994377,
-            "max": 0.26663347656634745,
-            "count": 335
+            "value": -0.07970754661650029,
+            "min": -0.26102524301380786,
+            "max": 0.3510517215934293,
+            "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": 20.777999877929688,
-            "min": -86.93080031871796,
-            "max": 62.125600039958954,
-            "count": 335
+            "value": -16.89799988269806,
+            "min": -55.66319966316223,
+            "max": 81.4439994096756,
+            "count": 500
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": 0.09531192604554903,
-            "min": -0.381275439994377,
-            "max": 0.26663347656634745,
-            "count": 335
+            "value": -0.07970754661650029,
+            "min": -0.26102524301380786,
+            "max": 0.3510517215934293,
+            "count": 500
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": 20.777999877929688,
-            "min": -86.93080031871796,
-            "max": 62.125600039958954,
-            "count": 335
+            "value": -16.89799988269806,
+            "min": -55.66319966316223,
+            "max": 81.4439994096756,
+            "count": 500
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 335
+            "count": 500
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 335
+            "count": 500
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.01046212162455049,
-            "min": 0.009879295097471185,
-            "max": 0.014559235423075734,
-            "count": 51
+            "value": 0.012091718217061499,
+            "min": 0.009822013491066173,
+            "max": 0.015032402960059699,
+            "count": 76
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.01046212162455049,
-            "min": 0.009879295097471185,
-            "max": 0.014559235423075734,
-            "count": 51
+            "value": 0.012091718217061499,
+            "min": 0.009822013491066173,
+            "max": 0.015032402960059699,
+            "count": 76
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.05891079842112958,
-            "min": 0.04971672408282757,
-            "max": 0.05918900854885578,
-            "count": 51
+            "value": 0.05806648256257176,
+            "min": 0.05226881531998515,
+            "max": 0.059615218080580235,
+            "count": 76
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.05891079842112958,
-            "min": 0.04971672408282757,
-            "max": 0.05918900854885578,
-            "count": 51
+            "value": 0.05806648256257176,
+            "min": 0.05226881531998515,
+            "max": 0.059615218080580235,
+            "count": 76
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.05924153439700604,
-            "min": 0.051102403877303006,
-            "max": 0.05954511137679219,
-            "count": 51
+            "value": 0.05836009904742241,
+            "min": 0.0542876117862761,
+            "max": 0.06110596880316734,
+            "count": 76
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.05924153439700604,
-            "min": 0.051102403877303006,
-            "max": 0.05954511137679219,
-            "count": 51
+            "value": 0.05836009904742241,
+            "min": 0.0542876117862761,
+            "max": 0.06110596880316734,
+            "count": 76
         },
         "SoccerTwos.Policy.LearningRate.mean": {
-            "value": 6.4449295954992225e-09,
-            "min": 6.4449295954992225e-09,
-            "max": 0.00014248644558948728,
-            "count": 51
+            "value": 4.0553810392494676e-07,
+            "min": 4.0553810392494676e-07,
+            "max": 0.0001428860023203168,
+            "count": 76
         },
         "SoccerTwos.Policy.LearningRate.sum": {
-            "value": 6.4449295954992225e-09,
-            "min": 6.4449295954992225e-09,
-            "max": 0.00014248644558948728,
-            "count": 51
+            "value": 4.0553810392494676e-07,
+            "min": 4.0553810392494676e-07,
+            "max": 0.0001428860023203168,
+            "count": 76
         },
         "SoccerTwos.Policy.Epsilon.mean": {
-            "value": 0.10000085146159124,
-            "min": 0.10000085146159124,
-            "max": 0.11912103967704953,
-            "count": 51
+            "value": 0.10005440800688417,
+            "min": 0.10005440800688417,
+            "max": 0.11917465842958205,
+            "count": 76
         },
         "SoccerTwos.Policy.Epsilon.sum": {
-            "value": 0.10000085146159124,
-            "min": 0.10000085146159124,
-            "max": 0.11912103967704953,
-            "count": 51
+            "value": 0.10005440800688417,
+            "min": 0.10005440800688417,
+            "max": 0.11917465842958205,
+            "count": 76
         },
         "SoccerTwos.Policy.Beta.mean": {
-            "value": 1.0002659404254946e-05,
-            "min": 1.0002659404254946e-05,
-            "max": 6.972151274949521e-05,
-            "count": 51
+            "value": 1.0169934717551432e-05,
+            "min": 1.0169934717551432e-05,
+            "max": 6.988898235716646e-05,
+            "count": 76
         },
         "SoccerTwos.Policy.Beta.sum": {
-            "value": 1.0002659404254946e-05,
-            "min": 1.0002659404254946e-05,
-            "max": 6.972151274949521e-05,
-            "count": 51
+            "value": 1.0169934717551432e-05,
+            "min": 1.0169934717551432e-05,
+            "max": 6.988898235716646e-05,
+            "count": 76
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1710343829",
+        "start_time_seconds": "1710358573",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
         "command_line_arguments": "/home/stephan/.conda/envs/rl/bin/mlagents-learn ./ml-agents/config/poca/SoccerTwos.yaml --env=./ml-agents/training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos-read-deal --width=1280 --height=720 --resume",
         "mlagents_version": "1.1.0.dev0",
@@ -204,59 +204,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.2.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1710353568"
+        "end_time_seconds": "1710372965"
     },
-    "total": 9739.254863360999,
+    "total": 14392.268066103992,
     "count": 1,
-    "self": 0.270132729987381,
+    "self": 0.3203680879960302,
     "children": {
         "run_training.setup": {
-            "total": 0.018506341002648696,
+            "total": 0.017996288996073417,
             "count": 1,
-            "self": 0.018506341002648696
+            "self": 0.017996288996073417
         },
         "TrainerController.start_learning": {
-            "total": 9738.966224290009,
+            "total": 14391.929701727,
             "count": 1,
-            "self": 4.652608350283117,
+            "self": 7.222826109427842,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 4.244304390012985,
-                    "count": 7,
-                    "self": 4.244304390012985
+                    "total": 4.3356985290010925,
+                    "count": 10,
+                    "self": 4.3356985290010925
                 },
                 "TrainerController.advance": {
-                    "total": 9729.947026144713,
-                    "count": 239073,
-                    "self": 4.148107524248189,
+                    "total": 14380.252779454575,
+                    "count": 357131,
+                    "self": 6.432589866788476,
                     "children": {
                         "env_step": {
-                            "total": 4354.3673745146225,
-                            "count": 239073,
-                            "self": 3721.0493522615725,
+                            "total": 6466.631959918537,
+                            "count": 357131,
+                            "self": 5498.500712261317,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 630.4299217515072,
-                                    "count": 239073,
-                                    "self": 19.02124206413282,
+                                    "total": 963.7606686544896,
+                                    "count": 357131,
+                                    "self": 29.2971219017345,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 611.4086796873744,
-                                            "count": 418182,
-                                            "self": 611.4086796873744
+                                            "total": 934.4635467527551,
+                                            "count": 624880,
+                                            "self": 934.4635467527551
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 2.8881005015427945,
-                                    "count": 239073,
+                                    "total": 4.370579002730665,
+                                    "count": 357131,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 9731.739510110943,
-                                            "count": 239073,
+                                            "total": 14380.838316511697,
+                                            "count": 357131,
                                             "is_parallel": true,
-                                            "self": 6533.360267171403,
+                                            "self": 9673.599672775075,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -265,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.06389564499841072,
+                                                            "total": 0.06619343400234357,
                                                             "count": 2,
                                                             "is_parallel": true,
-                                                            "self": 0.000593470991589129,
+                                                            "self": 0.0004880309716099873,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.06330217400682159,
+                                                                    "total": 0.06570540303073358,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.06330217400682159
+                                                                    "self": 0.06570540303073358
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.02612613000383135,
+                                                            "total": 0.027265490003628656,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.000600070008658804,
+                                                            "self": 0.0006784550059819594,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00040655999328009784,
+                                                                    "total": 0.0004930220020469278,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00040655999328009784
+                                                                    "self": 0.0004930220020469278
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.02343449799809605,
+                                                                    "total": 0.024494213997968473,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.02343449799809605
+                                                                    "self": 0.024494213997968473
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0016850020037963986,
+                                                                    "total": 0.0015997989976312965,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003057300054933876,
+                                                                    "self": 0.00032821799686644226,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001379271998303011,
+                                                                            "total": 0.0012715810007648543,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001379271998303011
+                                                                            "self": 0.0012715810007648543
                                                                         }
                                                                     }
                                                                 }
@@ -315,48 +315,48 @@
                                                     }
                                                 },
                                                 "steps_from_proto": {
-                                                    "total": 0.012151043978519738,
-                                                    "count": 12,
+                                                    "total": 0.018047201985609718,
+                                                    "count": 18,
                                                     "is_parallel": true,
-                                                    "self": 0.002059131977148354,
+                                                    "self": 0.0030916809337213635,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.010091912001371384,
-                                                            "count": 48,
+                                                            "total": 0.014955521051888354,
+                                                            "count": 72,
                                                             "is_parallel": true,
-                                                            "self": 0.010091912001371384
+                                                            "self": 0.014955521051888354
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 3198.3670918955613,
-                                                    "count": 239072,
+                                                    "total": 4707.220596534637,
+                                                    "count": 357130,
                                                     "is_parallel": true,
-                                                    "self": 175.16570653802773,
+                                                    "self": 257.41373912687413,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 110.43290661888022,
-                                                            "count": 239072,
+                                                            "total": 162.74674167780904,
+                                                            "count": 357130,
                                                             "is_parallel": true,
-                                                            "self": 110.43290661888022
+                                                            "self": 162.74674167780904
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 2470.8126502879313,
-                                                            "count": 239072,
+                                                            "total": 3645.2510425291694,
+                                                            "count": 357130,
                                                             "is_parallel": true,
-                                                            "self": 2470.8126502879313
+                                                            "self": 3645.2510425291694
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 441.95582845072204,
-                                                            "count": 478144,
+                                                            "total": 641.809073200784,
+                                                            "count": 714260,
                                                             "is_parallel": true,
-                                                            "self": 78.3687699053844,
+                                                            "self": 114.93468356617086,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 363.58705854533764,
-                                                                    "count": 1912576,
+                                                                    "total": 526.8743896346132,
+                                                                    "count": 2857040,
                                                                     "is_parallel": true,
-                                                                    "self": 363.58705854533764
+                                                                    "self": 526.8743896346132
                                                                 }
                                                             }
                                                         }
@@ -369,31 +369,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 5371.4315441058425,
-                            "count": 239073,
-                            "self": 26.83088273082103,
+                            "total": 7907.188229669249,
+                            "count": 357131,
+                            "self": 41.56422363645106,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 1094.2377518599678,
-                                    "count": 239073,
-                                    "self": 1093.3974272879568,
+                                    "total": 1667.4114032577781,
+                                    "count": 357131,
+                                    "self": 1666.2047581057705,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.8403245720110135,
-                                            "count": 7,
-                                            "self": 0.8403245720110135
+                                            "total": 1.2066451520076953,
+                                            "count": 10,
+                                            "self": 1.2066451520076953
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 4250.362909515054,
-                                    "count": 51,
-                                    "self": 652.032682771809,
+                                    "total": 6198.21260277502,
+                                    "count": 76,
+                                    "self": 967.3907746167824,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 3598.3302267432446,
-                                            "count": 4080,
-                                            "self": 3598.3302267432446
+                                            "total": 5230.821828158238,
+                                            "count": 6080,
+                                            "self": 5230.821828158238
                                         }
                                     }
                                 }
@@ -402,19 +402,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.200011845678091e-07,
+                    "total": 7.199996616691351e-07,
                     "count": 1,
-                    "self": 9.200011845678091e-07
+                    "self": 7.199996616691351e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.12228448499809019,
+                    "total": 0.11839691399654839,
                     "count": 1,
-                    "self": 0.0026952329935738817,
+                    "self": 0.0024417589884251356,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.11958925200451631,
+                            "total": 0.11595515500812326,
                             "count": 1,
-                            "self": 0.11958925200451631
+                            "self": 0.11595515500812326
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,59 +2,59 @@
     "SoccerTwos": {
         "checkpoints": [
             {
-                "steps": 8499978,
-                "file_path": "results/SoccerTwos-read-deal/SoccerTwos/SoccerTwos-8499978.onnx",
+                "steps": 13499994,
+                "file_path": "results/SoccerTwos-read-deal/SoccerTwos/SoccerTwos-13499994.onnx",
                 "reward": 0.0,
-                "creation_time": 1710349255.752344,
+                "creation_time": 1710368642.601263,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos-read-deal/SoccerTwos/SoccerTwos-8499978.pt"
+                    "results/SoccerTwos-read-deal/SoccerTwos/SoccerTwos-13499994.pt"
                 ]
             },
             {
-                "steps": 8999988,
-                "file_path": "results/SoccerTwos-read-deal/SoccerTwos/SoccerTwos-8999988.onnx",
+                "steps": 13999986,
+                "file_path": "results/SoccerTwos-read-deal/SoccerTwos/SoccerTwos-13999986.onnx",
                 "reward": 0.0,
-                "creation_time": 1710350638.0742688,
+                "creation_time": 1710370035.9879289,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos-read-deal/SoccerTwos/SoccerTwos-8999988.pt"
+                    "results/SoccerTwos-read-deal/SoccerTwos/SoccerTwos-13999986.pt"
                 ]
             },
             {
-                "steps": 9499993,
-                "file_path": "results/SoccerTwos-read-deal/SoccerTwos/SoccerTwos-9499993.onnx",
+                "steps": 14499998,
+                "file_path": "results/SoccerTwos-read-deal/SoccerTwos/SoccerTwos-14499998.onnx",
                 "reward": 0.0,
-                "creation_time": 1710352100.153916,
+                "creation_time": 1710371506.4123518,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos-read-deal/SoccerTwos/SoccerTwos-9499993.pt"
+                    "results/SoccerTwos-read-deal/SoccerTwos/SoccerTwos-14499998.pt"
                 ]
             },
             {
-                "steps": 9999982,
-                "file_path": "results/SoccerTwos-read-deal/SoccerTwos/SoccerTwos-9999982.onnx",
-                "reward": null,
-                "creation_time": 1710353568.109763,
+                "steps": 14999982,
+                "file_path": "results/SoccerTwos-read-deal/SoccerTwos/SoccerTwos-14999982.onnx",
+                "reward": 0.0,
+                "creation_time": 1710372965.343914,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos-read-deal/SoccerTwos/SoccerTwos-9999982.pt"
+                    "results/SoccerTwos-read-deal/SoccerTwos/SoccerTwos-14999982.pt"
                 ]
             },
             {
-                "steps": 10000046,
-                "file_path": "results/SoccerTwos-read-deal/SoccerTwos/SoccerTwos-10000046.onnx",
-                "reward": null,
-                "creation_time": 1710353568.2486105,
+                "steps": 15000014,
+                "file_path": "results/SoccerTwos-read-deal/SoccerTwos/SoccerTwos-15000014.onnx",
+                "reward": 0.0,
+                "creation_time": 1710372965.4699337,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos-read-deal/SoccerTwos/SoccerTwos-10000046.pt"
+                    "results/SoccerTwos-read-deal/SoccerTwos/SoccerTwos-15000014.pt"
                 ]
             }
         ],
-        "elo": 1607.9046472284606,
+        "elo": 1672.598696535884,
         "final_checkpoint": {
-            "steps": 10000046,
+            "steps": 15000014,
             "file_path": "results/SoccerTwos-read-deal/SoccerTwos.onnx",
-            "reward": null,
-            "creation_time": 1710353568.2486105,
+            "reward": 0.0,
+            "creation_time": 1710372965.4699337,
             "auxillary_file_paths": [
-                "results/SoccerTwos-read-deal/SoccerTwos/SoccerTwos-10000046.pt"
+                "results/SoccerTwos-read-deal/SoccerTwos/SoccerTwos-15000014.pt"
             ]
         }
     },