Update_agent

SoccerTwos/SoccerTwos-10348472.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9565db4d50e0dbef463f52b139b5a5974a8da3ef61c0c825f71958641df9c393
+size 241

SoccerTwos/SoccerTwos-8999993.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0b9a2752943a759e7b67b045d1f7f6577edc7f2c9259dbe3d6664a9db40954f
+size 886472

SoccerTwos/SoccerTwos-8999993.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e7b837f9f26ca5e829c75c62b3677fd379d321995f7748d6a2082a07df34e55
+size 10303217

SoccerTwos/SoccerTwos-9499966.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1730615fe73eaff7e38ecbd38ab079f3fac1a44b5265e86326a964957554da20
+size 886472

SoccerTwos/SoccerTwos-9499966.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cffd06b2af4432fd9c15f54927498abc7913e3fe3be434b74a3b0103ea5e8b5f
+size 10303217

SoccerTwos/SoccerTwos-9999992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:106025e439b4950b26dd593afe2824b282ec3f380b94c2c05933cbe7aab4f3da
+size 886472

SoccerTwos/SoccerTwos-9999992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:631c93e41924164b6d4fe209dd7e74520a46159b919af6a137f6a66c94f0778b
+size 10303217

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcdd305135887bb866efcff63ef1d98c0c7cbc67d192e3db571e45a8a06c8ba1
+oid sha256:631c93e41924164b6d4fe209dd7e74520a46159b919af6a137f6a66c94f0778b
 size 10303217

SoccerTwos/events.out.tfevents.1691323073.51fdecdbc575.8620.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b7cc1e0f14eb966c29494144bd544c62cdaecf75837e49b2fa10816dbae07eb
+size 1429714

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.99, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.95, "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": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 60000, "team_change": 225000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.25, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": "cpu"}, "debug": false}
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.99, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.95, "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": 12500000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 60000, "team_change": 225000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.25, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": "cpu"}, "debug": false}

configuration.yaml

@@ -37,7 +37,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 10000000
+    max_steps: 12500000
     time_horizon: 1000
     summary_freq: 10000
     threaded: false

run_logs/Player-0.log

@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/SoccerTwos_Data/Man
 Mono config path = '/content/ml-agents/training-envs-executables/SoccerTwos_Data/MonoBleedingEdge/etc'
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/SoccerTwos
-Unable to load player prefs
 Initialize engine version: 2021.3.14f1 (eee1884e7226)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/SoccerTwos_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.160 seconds
+- Completed reload, in  0.235 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -59,7 +56,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.856664 ms
+UnloadTime: 7.297608 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
@@ -68,7 +65,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 8514 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 26251 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
@@ -184,19 +181,19 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 4
+  Peak main deferred allocation count 3
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 8515 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 26252 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 4.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 8515 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 26252 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 17.6 MB
@@ -228,13 +225,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 8514 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 26251 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 65.6 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [128.0 KB-256.0 KB]: 8515 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 26252 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -246,16 +243,16 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 8515 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 26252 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 0.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 8514 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 26251 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
-      Peak Allocated memory 4.2 MB
+      Peak Allocated memory 4.4 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
@@ -264,13 +261,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 8515 frames
+      Peak usage frame count: [0-1.0 KB]: 26252 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]: 8514 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 26251 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": 2.2750937938690186,
-            "min": 2.237426519393921,
-            "max": 2.4118874073028564,
-            "count": 45
+            "value": 2.0817551612854004,
+            "min": 2.050828218460083,
+            "max": 2.275116205215454,
+            "count": 139
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 45793.08984375,
-            "min": 42230.7265625,
-            "max": 57216.2578125,
-            "count": 45
+            "value": 42900.8125,
+            "min": 39650.84375,
+            "max": 50390.9765625,
+            "count": 139
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 56.63953488372093,
-            "min": 42.29661016949152,
-            "max": 61.325,
-            "count": 45
+            "value": 39.314516129032256,
+            "min": 33.28082191780822,
+            "max": 57.25581395348837,
+            "count": 139
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19484.0,
-            "min": 19048.0,
-            "max": 20140.0,
-            "count": 45
+            "value": 19500.0,
+            "min": 16104.0,
+            "max": 20308.0,
+            "count": 139
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1482.6735168891223,
-            "min": 1447.8964098134252,
-            "max": 1498.4113615420426,
-            "count": 45
+            "value": 1514.2101837328041,
+            "min": 1476.4009957931617,
+            "max": 1527.4014633986794,
+            "count": 139
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 255019.84490492905,
-            "min": 235665.1365983267,
-            "max": 350803.6744841606,
-            "count": 45
+            "value": 375524.12556573545,
+            "min": 256817.66796581444,
+            "max": 441113.2119379982,
+            "count": 139
         },
         "SoccerTwos.Step.mean": {
-            "value": 8949979.0,
-            "min": 8509934.0,
-            "max": 8949979.0,
-            "count": 45
+            "value": 10339990.0,
+            "min": 8959951.0,
+            "max": 10339990.0,
+            "count": 139
         },
         "SoccerTwos.Step.sum": {
-            "value": 8949979.0,
-            "min": 8509934.0,
-            "max": 8949979.0,
-            "count": 45
+            "value": 10339990.0,
+            "min": 8959951.0,
+            "max": 10339990.0,
+            "count": 139
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.004916130565106869,
-            "min": -0.03196634352207184,
-            "max": 0.07559280097484589,
-            "count": 45
+            "value": 0.01461908221244812,
+            "min": -0.04508669674396515,
+            "max": 0.06564339250326157,
+            "count": 139
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -0.8504905700683594,
-            "min": -5.49821138381958,
-            "max": 16.894067764282227,
-            "count": 45
+            "value": 3.6109132766723633,
+            "min": -9.310239791870117,
+            "max": 16.082632064819336,
+            "count": 139
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.0044533200562000275,
-            "min": -0.03109934739768505,
-            "max": 0.07799124717712402,
-            "count": 45
+            "value": 0.015170346014201641,
+            "min": -0.04868944361805916,
+            "max": 0.06690935045480728,
+            "count": 139
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -0.7704243659973145,
-            "min": -5.349087715148926,
-            "max": 16.790143966674805,
-            "count": 45
+            "value": 3.7470755577087402,
+            "min": -9.785125732421875,
+            "max": 16.198457717895508,
+            "count": 139
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 45
+            "count": 139
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 45
+            "count": 139
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.03477225551715476,
-            "min": -0.21960648588232093,
-            "max": 0.2603318790160933,
-            "count": 45
+            "value": 0.014383805908172237,
+            "min": -0.1816229159012437,
+            "max": 0.21367312527963245,
+            "count": 139
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -6.015600204467773,
-            "min": -40.62719988822937,
-            "max": 59.616000294685364,
-            "count": 45
+            "value": 3.5528000593185425,
+            "min": -36.445600390434265,
+            "max": 48.50379943847656,
+            "count": 139
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.03477225551715476,
-            "min": -0.21960648588232093,
-            "max": 0.2603318790160933,
-            "count": 45
+            "value": 0.014383805908172237,
+            "min": -0.1816229159012437,
+            "max": 0.21367312527963245,
+            "count": 139
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -6.015600204467773,
-            "min": -40.62719988822937,
-            "max": 59.616000294685364,
-            "count": 45
+            "value": 3.5528000593185425,
+            "min": -36.445600390434265,
+            "max": 48.50379943847656,
+            "count": 139
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 45
+            "count": 139
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 45
+            "count": 139
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.019061286328117908,
-            "min": 0.013057671172039894,
-            "max": 0.021450920356437565,
-            "count": 21
+            "value": 0.014852080177903796,
+            "min": 0.009855266399487543,
+            "max": 0.022194832651378723,
+            "count": 67
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.019061286328117908,
-            "min": 0.013057671172039894,
-            "max": 0.021450920356437565,
-            "count": 21
+            "value": 0.014852080177903796,
+            "min": 0.009855266399487543,
+            "max": 0.022194832651378723,
+            "count": 67
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.08023651391267776,
-            "min": 0.06944796616832415,
-            "max": 0.08236863935987154,
-            "count": 21
+            "value": 0.08246669918298721,
+            "min": 0.07240680480996768,
+            "max": 0.0872135025759538,
+            "count": 67
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.08023651391267776,
-            "min": 0.06944796616832415,
-            "max": 0.08236863935987154,
-            "count": 21
+            "value": 0.08246669918298721,
+            "min": 0.07240680480996768,
+            "max": 0.0872135025759538,
+            "count": 67
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.0812089612086614,
-            "min": 0.07063307439287504,
-            "max": 0.08386725783348084,
-            "count": 21
+            "value": 0.08406391814351082,
+            "min": 0.07332472875714302,
+            "max": 0.08962557539343834,
+            "count": 67
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.0812089612086614,
-            "min": 0.07063307439287504,
-            "max": 0.08386725783348084,
-            "count": 21
+            "value": 0.08406391814351082,
+            "min": 0.07332472875714302,
+            "max": 0.08962557539343834,
+            "count": 67
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 21
+            "count": 67
         },
         "SoccerTwos.Policy.LearningRate.sum": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 21
+            "count": 67
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.20000000000000007,
             "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 21
+            "count": 67
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.20000000000000007,
             "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 21
+            "count": 67
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.005000000000000001,
             "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 21
+            "count": 67
         },
         "SoccerTwos.Policy.Beta.sum": {
             "value": 0.005000000000000001,
             "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 21
+            "count": 67
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1691321389",
+        "start_time_seconds": "1691323071",
         "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume --torch-device=cpu",
         "mlagents_version": "0.31.0.dev0",
@@ -204,59 +204,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1691323056"
+        "end_time_seconds": "1691328379"
     },
-    "total": 1666.35867087,
+    "total": 5307.499628232,
     "count": 1,
-    "self": 0.1516258750000361,
+    "self": 0.5378562470004908,
     "children": {
         "run_training.setup": {
-            "total": 0.0630226039999684,
+            "total": 0.06018139100001463,
             "count": 1,
-            "self": 0.0630226039999684
+            "self": 0.06018139100001463
         },
         "TrainerController.start_learning": {
-            "total": 1666.144022391,
+            "total": 5306.901590594,
             "count": 1,
-            "self": 1.125772229994709,
+            "self": 3.954543449065568,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.8054959460000646,
-                    "count": 4,
-                    "self": 3.8054959460000646
+                    "total": 1.757532165000839,
+                    "count": 8,
+                    "self": 1.757532165000839
                 },
                 "TrainerController.advance": {
-                    "total": 1660.728283220005,
-                    "count": 31775,
-                    "self": 1.17107058898182,
+                    "total": 5301.185609296934,
+                    "count": 99781,
+                    "self": 4.008114537936308,
                     "children": {
                         "env_step": {
-                            "total": 923.7054244490093,
-                            "count": 31775,
-                            "self": 787.9239653509692,
+                            "total": 2931.331986786951,
+                            "count": 99781,
+                            "self": 2508.7911618191483,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 135.0932160220205,
-                                    "count": 31775,
-                                    "self": 6.267143035018819,
+                                    "total": 420.3306268819065,
+                                    "count": 99781,
+                                    "self": 18.73769292570705,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 128.82607298700168,
-                                            "count": 56764,
-                                            "self": 128.82607298700168
+                                            "total": 401.59293395619943,
+                                            "count": 175010,
+                                            "self": 401.59293395619943
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.688243076019603,
-                                    "count": 31774,
+                                    "total": 2.2101980858960815,
+                                    "count": 99780,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1660.719618600975,
-                                            "count": 31774,
+                                            "total": 5284.2023605070735,
+                                            "count": 99780,
                                             "is_parallel": true,
-                                            "self": 998.2839195230074,
+                                            "self": 3188.8961787200533,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -265,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.009984467000037966,
+                                                            "total": 0.004170569000052637,
                                                             "count": 2,
                                                             "is_parallel": true,
-                                                            "self": 0.005311473000119804,
+                                                            "self": 0.0011218869999538583,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0046729939999181624,
+                                                                    "total": 0.003048682000098779,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0046729939999181624
+                                                                    "self": 0.003048682000098779
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.05700391100003799,
+                                                            "total": 0.04688210699987394,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0014013470000122652,
+                                                            "self": 0.0013496169997324614,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0006023120000122617,
+                                                                    "total": 0.0006175339999572316,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0006023120000122617
+                                                                    "self": 0.0006175339999572316
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04908923200002846,
+                                                                    "total": 0.040462964000198554,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04908923200002846
+                                                                    "self": 0.040462964000198554
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.005911019999985001,
+                                                                    "total": 0.004451991999985694,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00234404599990512,
+                                                                    "self": 0.0008053609999478795,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.003566974000079881,
+                                                                            "total": 0.0036466310000378144,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.003566974000079881
+                                                                            "self": 0.0036466310000378144
                                                                         }
                                                                     }
                                                                 }
@@ -315,48 +315,48 @@
                                                     }
                                                 },
                                                 "steps_from_proto": {
-                                                    "total": 0.011122505000230376,
-                                                    "count": 6,
+                                                    "total": 0.019279038001741355,
+                                                    "count": 14,
                                                     "is_parallel": true,
-                                                    "self": 0.0018661929996142135,
+                                                    "self": 0.0034742869997899106,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.009256312000616163,
-                                                            "count": 24,
+                                                            "total": 0.015804751001951445,
+                                                            "count": 56,
                                                             "is_parallel": true,
-                                                            "self": 0.009256312000616163
+                                                            "self": 0.015804751001951445
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 662.4245765729675,
-                                                    "count": 31773,
+                                                    "total": 2095.2869027490187,
+                                                    "count": 99779,
                                                     "is_parallel": true,
-                                                    "self": 40.155766980000635,
+                                                    "self": 125.02009742788687,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 20.78963876998432,
-                                                            "count": 31773,
+                                                            "total": 64.16027218404838,
+                                                            "count": 99779,
                                                             "is_parallel": true,
-                                                            "self": 20.78963876998432
+                                                            "self": 64.16027218404838
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 472.86539670498286,
-                                                            "count": 31773,
+                                                            "total": 1498.7004830649933,
+                                                            "count": 99779,
                                                             "is_parallel": true,
-                                                            "self": 472.86539670498286
+                                                            "self": 1498.7004830649933
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 128.6137741179997,
-                                                            "count": 63546,
+                                                            "total": 407.40605007209024,
+                                                            "count": 199558,
                                                             "is_parallel": true,
-                                                            "self": 22.407620258942643,
+                                                            "self": 72.04748076905344,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 106.20615385905705,
-                                                                    "count": 254184,
+                                                                    "total": 335.3585693030368,
+                                                                    "count": 798232,
                                                                     "is_parallel": true,
-                                                                    "self": 106.20615385905705
+                                                                    "self": 335.3585693030368
                                                                 }
                                                             }
                                                         }
@@ -369,24 +369,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 735.8517881820139,
-                            "count": 31774,
-                            "self": 7.557935876023976,
+                            "total": 2365.8455079720466,
+                            "count": 99780,
+                            "self": 25.670958199969846,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 150.53404438198953,
-                                    "count": 31774,
-                                    "self": 150.53404438198953
+                                    "total": 507.6338691290741,
+                                    "count": 99780,
+                                    "self": 506.59619934807483,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 1.0376697809992947,
+                                            "count": 3,
+                                            "self": 1.0376697809992947
+                                        }
+                                    }
                                 },
                                 "_update_policy": {
-                                    "total": 577.7598079240004,
-                                    "count": 21,
-                                    "self": 107.79722011599904,
+                                    "total": 1832.5406806430028,
+                                    "count": 67,
+                                    "self": 356.4519601630159,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 469.96258780800133,
-                                            "count": 630,
-                                            "self": 469.96258780800133
+                                            "total": 1476.088720479987,
+                                            "count": 2010,
+                                            "self": 1476.088720479987
                                         }
                                     }
                                 }
@@ -395,19 +402,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.610000026630587e-06,
+                    "total": 1.538999640615657e-06,
                     "count": 1,
-                    "self": 1.610000026630587e-06
+                    "self": 1.538999640615657e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.48446938500001124,
+                    "total": 0.0039041439995344263,
                     "count": 1,
-                    "self": 0.0020487920000960003,
+                    "self": 6.911199943715474e-05,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.48242059299991524,
+                            "total": 0.0038350320000972715,
                             "count": 1,
-                            "self": 0.48242059299991524
+                            "self": 0.0038350320000972715
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,52 +2,52 @@
     "SoccerTwos": {
         "checkpoints": [
             {
-                "steps": 7999862,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-7999862.onnx",
+                "steps": 8500054,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8500054.onnx",
                 "reward": 0.0,
-                "creation_time": 1690983530.4329538,
+                "creation_time": 1690985799.4838839,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-7999862.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8500054.pt"
                 ]
             },
             {
-                "steps": 8000190,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8000190.onnx",
+                "steps": 8951810,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8951810.onnx",
                 "reward": 0.0,
-                "creation_time": 1690983530.7166526,
+                "creation_time": 1691323056.1832547,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8000190.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8951810.pt"
                 ]
             },
             {
-                "steps": 8499950,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8499950.onnx",
+                "steps": 8999993,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8999993.onnx",
                 "reward": 0.0,
-                "creation_time": 1690985799.0996766,
+                "creation_time": 1691323250.2108784,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8499950.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8999993.pt"
                 ]
             },
             {
-                "steps": 8500054,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8500054.onnx",
+                "steps": 9499966,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-9499966.onnx",
                 "reward": 0.0,
-                "creation_time": 1690985799.4838839,
+                "creation_time": 1691325176.6160336,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8500054.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-9499966.pt"
                 ]
             },
             {
-                "steps": 8951810,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8951810.onnx",
+                "steps": 9999992,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-9999992.onnx",
                 "reward": 0.0,
-                "creation_time": 1691323056.1832547,
+                "creation_time": 1691327051.966959,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8951810.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-9999992.pt"
                 ]
             }
         ],
-        "elo": 1481.2444578197278,
+        "elo": 1508.9473185543081,
         "final_checkpoint": {
             "steps": 8951810,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",