Update_agent

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25e6238c1544dd847cd8f7534693c008b28cd3db1716f739dd722dcb17d7c69e
+oid sha256:701601c692c8d238aa851ab21839437e28501a713c318ee13ca0a54c2103592f
 size 886472

SoccerTwos/SoccerTwos-8499950.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:701601c692c8d238aa851ab21839437e28501a713c318ee13ca0a54c2103592f
+size 886472

SoccerTwos/SoccerTwos-8499950.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56b6968265843c54ca73f4c5ffff2e7cdd56c5c436b117fe54365426b4491e0e
+size 10303217

SoccerTwos/SoccerTwos-8500054.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:701601c692c8d238aa851ab21839437e28501a713c318ee13ca0a54c2103592f
+size 886472

SoccerTwos/SoccerTwos-8500054.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e217a3b83aa41da13285d6b53530ea195f471deddaba40339ffd47c5e2864a03
+size 10303217

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:525ee6ecec7f3e0bfe3e28ddd4c7e94cf3a9745d7701b438b39f5aff2debdd1d
+oid sha256:e217a3b83aa41da13285d6b53530ea195f471deddaba40339ffd47c5e2864a03
 size 10303217

SoccerTwos/events.out.tfevents.1690983639.cd7f5c1d4207.18652.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36f351104635f04acb0c6f7df6836c1dda81d8918f644081584927735efee878
+size 515045

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": 8000000, "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": 8500000, "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: 8000000
+    max_steps: 8500000
     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  0.296 seconds
+- Completed reload, in  0.286 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: 1.725021 ms
+UnloadTime: 0.956290 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]: 18807 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 9427 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 5
     [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]: 18808 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 9428 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]: 18808 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 9428 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]: 18807 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 9427 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]: 18808 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 9428 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -246,15 +243,15 @@ 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]: 18808 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 9428 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]: 18807 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 9427 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
-      Peak Block count 2
+      Peak Block count 1
       Peak Allocated memory 4.0 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
@@ -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]: 18808 frames
+      Peak usage frame count: [0-1.0 KB]: 9428 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]: 18807 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 9427 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": 2.371412754058838,
-            "min": 2.2087302207946777,
-            "max": 2.39727520942688,
-            "count": 100
+            "value": 2.380178213119507,
+            "min": 2.316612958908081,
+            "max": 2.455829620361328,
+            "count": 50
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 48262.9921875,
-            "min": 42528.58203125,
-            "max": 49591.15625,
-            "count": 100
+            "value": 48212.890625,
+            "min": 44380.87109375,
+            "max": 54224.71875,
+            "count": 50
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 51.49484536082474,
-            "min": 38.65873015873016,
-            "max": 55.75,
-            "count": 100
+            "value": 52.75268817204301,
+            "min": 42.875,
+            "max": 63.96103896103896,
+            "count": 50
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19980.0,
-            "min": 18784.0,
-            "max": 20280.0,
-            "count": 100
+            "value": 19624.0,
+            "min": 18408.0,
+            "max": 20700.0,
+            "count": 50
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1463.392093878625,
-            "min": 1445.8863063509434,
-            "max": 1507.9787189382319,
-            "count": 100
+            "value": 1442.148207290123,
+            "min": 1424.3106954821,
+            "max": 1462.656016811587,
+            "count": 50
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 283898.06621245324,
-            "min": 256630.49491822318,
-            "max": 376018.87725131586,
-            "count": 100
+            "value": 268239.5665559629,
+            "min": 219343.8471042434,
+            "max": 327113.13015264703,
+            "count": 50
         },
         "SoccerTwos.Step.mean": {
-            "value": 7999862.0,
-            "min": 7009984.0,
-            "max": 7999862.0,
-            "count": 100
+            "value": 8499950.0,
+            "min": 8009922.0,
+            "max": 8499950.0,
+            "count": 50
         },
         "SoccerTwos.Step.sum": {
-            "value": 7999862.0,
-            "min": 7009984.0,
-            "max": 7999862.0,
-            "count": 100
+            "value": 8499950.0,
+            "min": 8009922.0,
+            "max": 8499950.0,
+            "count": 50
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.04442407190799713,
-            "min": -0.07316892594099045,
-            "max": 0.11921154707670212,
-            "count": 100
+            "value": 0.04855068400502205,
+            "min": -0.07220041751861572,
+            "max": 0.05768253281712532,
+            "count": 50
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -8.573845863342285,
-            "min": -16.243501663208008,
-            "max": 24.43836784362793,
-            "count": 100
+            "value": 9.030426979064941,
+            "min": -11.191064834594727,
+            "max": 9.863713264465332,
+            "count": 50
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.0450684055685997,
-            "min": -0.0768783837556839,
-            "max": 0.11984899640083313,
-            "count": 100
+            "value": 0.05044595152139664,
+            "min": -0.0745588093996048,
+            "max": 0.05884367972612381,
+            "count": 50
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -8.698202133178711,
-            "min": -17.067001342773438,
-            "max": 24.56904411315918,
-            "count": 100
+            "value": 9.382946968078613,
+            "min": -11.556615829467773,
+            "max": 10.06226921081543,
+            "count": 50
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 100
+            "count": 50
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 100
+            "count": 50
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.15272331546625326,
-            "min": -0.30646943088640205,
-            "max": 0.33254048708008555,
-            "count": 100
+            "value": 0.2131462359941134,
+            "min": -0.3135668301000828,
+            "max": 0.2131462359941134,
+            "count": 50
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -29.475599884986877,
-            "min": -59.14860016107559,
-            "max": 68.17079985141754,
-            "count": 100
+            "value": 39.64519989490509,
+            "min": -64.28120017051697,
+            "max": 39.64519989490509,
+            "count": 50
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.15272331546625326,
-            "min": -0.30646943088640205,
-            "max": 0.33254048708008555,
-            "count": 100
+            "value": 0.2131462359941134,
+            "min": -0.3135668301000828,
+            "max": 0.2131462359941134,
+            "count": 50
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -29.475599884986877,
-            "min": -59.14860016107559,
-            "max": 68.17079985141754,
-            "count": 100
+            "value": 39.64519989490509,
+            "min": -64.28120017051697,
+            "max": 39.64519989490509,
+            "count": 50
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 100
+            "count": 50
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 100
+            "count": 50
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.016550519535667264,
-            "min": 0.012449445958676126,
-            "max": 0.02179399854503572,
-            "count": 48
+            "value": 0.023197830274390676,
+            "min": 0.013356867283194636,
+            "max": 0.023197830274390676,
+            "count": 24
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.016550519535667264,
-            "min": 0.012449445958676126,
-            "max": 0.02179399854503572,
-            "count": 48
+            "value": 0.023197830274390676,
+            "min": 0.013356867283194636,
+            "max": 0.023197830274390676,
+            "count": 24
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.07420279954870541,
-            "min": 0.0691191777586937,
-            "max": 0.08944011678298315,
-            "count": 48
+            "value": 0.07942844703793525,
+            "min": 0.07309874321023623,
+            "max": 0.08458008393645286,
+            "count": 24
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.07420279954870541,
-            "min": 0.0691191777586937,
-            "max": 0.08944011678298315,
-            "count": 48
+            "value": 0.07942844703793525,
+            "min": 0.07309874321023623,
+            "max": 0.08458008393645286,
+            "count": 24
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.07562136252721151,
-            "min": 0.07054731796185175,
-            "max": 0.09129000231623649,
-            "count": 48
+            "value": 0.08078471745053926,
+            "min": 0.07401245236396789,
+            "max": 0.08580805708964666,
+            "count": 24
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.07562136252721151,
-            "min": 0.07054731796185175,
-            "max": 0.09129000231623649,
-            "count": 48
+            "value": 0.08078471745053926,
+            "min": 0.07401245236396789,
+            "max": 0.08580805708964666,
+            "count": 24
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 48
+            "count": 24
         },
         "SoccerTwos.Policy.LearningRate.sum": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 48
+            "count": 24
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.20000000000000007,
             "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 48
+            "count": 24
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.20000000000000007,
             "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 48
+            "count": 24
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.005000000000000001,
             "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 48
+            "count": 24
         },
         "SoccerTwos.Policy.Beta.sum": {
             "value": 0.005000000000000001,
             "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 48
+            "count": 24
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1690979434",
+        "start_time_seconds": "1690983637",
         "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": "1690983531"
+        "end_time_seconds": "1690985800"
     },
-    "total": 4096.745443753,
+    "total": 2162.7106171739997,
     "count": 1,
-    "self": 0.6394406489998801,
+    "self": 0.9037419579990456,
     "children": {
         "run_training.setup": {
-            "total": 0.0784915739999974,
+            "total": 0.060675459000776755,
             "count": 1,
-            "self": 0.0784915739999974
+            "self": 0.060675459000776755
         },
         "TrainerController.start_learning": {
-            "total": 4096.02751153,
+            "total": 2161.746199757,
             "count": 1,
-            "self": 2.8281643430832446,
+            "self": 1.6191924019904036,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 8.65609116200028,
-                    "count": 6,
-                    "self": 8.65609116200028
+                    "total": 1.9989515810011653,
+                    "count": 4,
+                    "self": 1.9989515810011653
                 },
                 "TrainerController.advance": {
-                    "total": 4084.3313739339164,
-                    "count": 70998,
-                    "self": 2.994735133006998,
+                    "total": 2157.795428820008,
+                    "count": 35166,
+                    "self": 1.6563339889225972,
                     "children": {
                         "env_step": {
-                            "total": 2225.2680462719277,
-                            "count": 70998,
-                            "self": 1889.0934393509137,
+                            "total": 1182.5269893600162,
+                            "count": 35166,
+                            "self": 1000.763291206069,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 334.5323984190172,
-                                    "count": 70998,
-                                    "self": 15.19586764797532,
+                                    "total": 180.80081926900948,
+                                    "count": 35166,
+                                    "self": 8.761010321992217,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 319.3365307710419,
-                                            "count": 125386,
-                                            "self": 319.3365307710419
+                                            "total": 172.03980894701726,
+                                            "count": 62852,
+                                            "self": 172.03980894701726
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 1.6422085019966062,
-                                    "count": 70998,
+                                    "total": 0.9628788849377088,
+                                    "count": 35166,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 4073.925150491917,
-                                            "count": 70998,
+                                            "total": 2149.7575688819506,
+                                            "count": 35166,
                                             "is_parallel": true,
-                                            "self": 2505.7642747309687,
+                                            "self": 1323.851014691044,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -265,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.018374151000045913,
+                                                            "total": 0.004038815000967588,
                                                             "count": 2,
                                                             "is_parallel": true,
-                                                            "self": 0.0119667230000573,
+                                                            "self": 0.0010986500010403688,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.006407427999988613,
+                                                                    "total": 0.0029401649999272195,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.006407427999988613
+                                                                    "self": 0.0029401649999272195
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.09766891499998565,
+                                                            "total": 0.04927174800013745,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0014384779999545572,
+                                                            "self": 0.0015231150000545313,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0009897369999976036,
+                                                                    "total": 0.0009635169999455684,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0009897369999976036
+                                                                    "self": 0.0009635169999455684
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.09064448100002664,
+                                                                    "total": 0.04162817599990376,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.09064448100002664
+                                                                    "self": 0.04162817599990376
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.00459621900000684,
+                                                                    "total": 0.00515694000023359,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0008003490000305646,
+                                                                    "self": 0.0012330029994700453,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0037958699999762757,
+                                                                            "total": 0.003923937000763544,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0037958699999762757
+                                                                            "self": 0.003923937000763544
                                                                         }
                                                                     }
                                                                 }
@@ -315,48 +315,48 @@
                                                     }
                                                 },
                                                 "steps_from_proto": {
-                                                    "total": 0.013870440999937728,
-                                                    "count": 10,
+                                                    "total": 0.007358864001616894,
+                                                    "count": 6,
                                                     "is_parallel": true,
-                                                    "self": 0.0025151149995394917,
+                                                    "self": 0.0014059410013942397,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.011355326000398236,
-                                                            "count": 40,
+                                                            "total": 0.005952923000222654,
+                                                            "count": 24,
                                                             "is_parallel": true,
-                                                            "self": 0.011355326000398236
+                                                            "self": 0.005952923000222654
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1568.1470053199484,
-                                                    "count": 70997,
+                                                    "total": 825.8991953269051,
+                                                    "count": 35165,
                                                     "is_parallel": true,
-                                                    "self": 95.8601831498911,
+                                                    "self": 49.1085151828147,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 48.96301269501026,
-                                                            "count": 70997,
+                                                            "total": 25.941193363029015,
+                                                            "count": 35165,
                                                             "is_parallel": true,
-                                                            "self": 48.96301269501026
+                                                            "self": 25.941193363029015
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1122.841477909058,
-                                                            "count": 70997,
+                                                            "total": 599.1414160830236,
+                                                            "count": 35165,
                                                             "is_parallel": true,
-                                                            "self": 1122.841477909058
+                                                            "self": 599.1414160830236
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 300.4823315659889,
-                                                            "count": 141994,
+                                                            "total": 151.70807069803777,
+                                                            "count": 70330,
                                                             "is_parallel": true,
-                                                            "self": 53.178555826181196,
+                                                            "self": 27.51554457509519,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 247.3037757398077,
-                                                                    "count": 567976,
+                                                                    "total": 124.19252612294258,
+                                                                    "count": 281320,
                                                                     "is_parallel": true,
-                                                                    "self": 247.3037757398077
+                                                                    "self": 124.19252612294258
                                                                 }
                                                             }
                                                         }
@@ -369,31 +369,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 1856.0685925289818,
-                            "count": 70998,
-                            "self": 19.105123239990917,
+                            "total": 973.6121054710693,
+                            "count": 35166,
+                            "self": 11.508108431125038,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 395.95893446499264,
-                                    "count": 70998,
-                                    "self": 395.2260836419924,
+                                    "total": 201.08197445894712,
+                                    "count": 35166,
+                                    "self": 200.7252909799472,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.7328508230002626,
-                                            "count": 2,
-                                            "self": 0.7328508230002626
+                                            "total": 0.35668347899991204,
+                                            "count": 1,
+                                            "self": 0.35668347899991204
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 1441.0045348239983,
-                                    "count": 48,
-                                    "self": 269.009414033,
+                                    "total": 761.0220225809971,
+                                    "count": 24,
+                                    "self": 138.21131571299338,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 1171.9951207909983,
-                                            "count": 1440,
-                                            "self": 1171.9951207909983
+                                            "total": 622.8107068680038,
+                                            "count": 720,
+                                            "self": 622.8107068680038
                                         }
                                     }
                                 }
@@ -402,19 +402,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.2710006558336318e-06,
+                    "total": 1.8259997887071222e-06,
                     "count": 1,
-                    "self": 1.2710006558336318e-06
+                    "self": 1.8259997887071222e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.21188081999935093,
+                    "total": 0.3326251280004726,
                     "count": 1,
-                    "self": 0.0022710239991283743,
+                    "self": 0.0030662400013170554,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.20960979600022256,
+                            "total": 0.32955888799915556,
                             "count": 1,
-                            "self": 0.20960979600022256
+                            "self": 0.32955888799915556
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,24 +1,6 @@
 {
     "SoccerTwos": {
         "checkpoints": [
-            {
-                "steps": 6999984,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-6999984.onnx",
-                "reward": 0.0,
-                "creation_time": 1690893541.6311257,
-                "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-6999984.pt"
-                ]
-            },
-            {
-                "steps": 7000018,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-7000018.onnx",
-                "reward": 0.0,
-                "creation_time": 1690893541.8556185,
-                "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-7000018.pt"
-                ]
-            },
             {
                 "steps": 7499987,
                 "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-7499987.onnx",
@@ -45,16 +27,34 @@
                 "auxillary_file_paths": [
                     "results/SoccerTwos/SoccerTwos/SoccerTwos-8000190.pt"
                 ]
+            },
+            {
+                "steps": 8499950,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8499950.onnx",
+                "reward": 0.0,
+                "creation_time": 1690985799.0996766,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8499950.pt"
+                ]
+            },
+            {
+                "steps": 8500054,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8500054.onnx",
+                "reward": 0.0,
+                "creation_time": 1690985799.4838839,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8500054.pt"
+                ]
             }
         ],
-        "elo": 1460.7618769520575,
+        "elo": 1450.2288314589186,
         "final_checkpoint": {
-            "steps": 8000190,
+            "steps": 8500054,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1690983530.7166526,
+            "creation_time": 1690985799.4838839,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-8000190.pt"
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-8500054.pt"
             ]
         }
     },