Rock n roll 2

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f25bb417690224bd8375ddc863f66f35de30d35231b9de51e69fe7cbdb9bf204
+oid sha256:f46fa7273456ecb3fcf39a98dd2c02251c2a305a598b0889fb44ca321408a751
 size 2815689

SoccerTwos/SoccerTwos-701120.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f46fa7273456ecb3fcf39a98dd2c02251c2a305a598b0889fb44ca321408a751
+size 2815689

SoccerTwos/SoccerTwos-701120.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6e2c9bdb7b5ec82738f6199c8323108d750cc8e3efc3a6a8491cd25df59335b
+size 34728689

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7e902c9997bb4e54ab800e41aa2ea801efe536c07bddc1071c862898d4dc20e
+oid sha256:e6e2c9bdb7b5ec82738f6199c8323108d750cc8e3efc3a6a8491cd25df59335b
 size 34728689

SoccerTwos/events.out.tfevents.1683407538.CLM-FVFF611QQ05P.local.67468.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cce24f10d5cdcf95f20d2dd05520cd61ace564c05ce6e5e2c5d11d808308e6a
+size 313108

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0002, "beta": 0.01, "epsilon": 0.25, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 2000000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.973, "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": 5000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 200000, "team_change": 200000, "swap_steps": 2000, "window": 50, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos/SoccerTwos.app", "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": false, "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": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.25, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 2000000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.973, "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": 5000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 200000, "team_change": 200000, "swap_steps": 2000, "window": 50, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos/SoccerTwos.app", "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": null}, "debug": false}

configuration.yaml

@@ -5,7 +5,7 @@ behaviors:
     hyperparameters:
       batch_size: 2048
       buffer_size: 20480
-      learning_rate: 0.0002
+      learning_rate: 0.0003
       beta: 0.01
       epsilon: 0.25
       lambd: 0.95
@@ -72,7 +72,7 @@ checkpoint_settings:
   run_id: SoccerTwos
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -10,7 +10,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.055 seconds
+- Completed reload, in  0.078 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)
@@ -35,7 +35,7 @@ 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: 0.399125 ms
+UnloadTime: 0.488750 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 TOO LONG
@@ -168,16 +168,14 @@ TOO LONG
 TOO LONG
 TOO LONG
 TOO LONG
-TOO LONG
-TOO LONG
 GRPC Exception: Status(StatusCode=Unknown, Detail="Exception calling application: [Errno 32] Broken pipe"). Disconnecting from trainer.
-Thread 0x16ec2b000 may have been prematurely finalized
+Thread 0x16f107000 may have been prematurely finalized
 Setting up 4 worker threads for Enlighten.
 Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 6428 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 7210 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
@@ -220,7 +218,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 5]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 0.7 KB
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
@@ -235,7 +233,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 4]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0.7 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 3]
       Initial Block Size 256.0 KB
@@ -328,22 +326,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 2
+  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]: 6429 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 7211 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 4.9 MB
+      Peak Allocated memory 4.8 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 6429 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 7211 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.5 MB
+      Peak Allocated memory 17.6 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -372,13 +370,13 @@ 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]: 6428 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 7210 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]: 6429 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 7211 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -390,13 +388,13 @@ 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]: 6429 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 7211 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]: 6428 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 7210 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 3.4 MB
@@ -408,13 +406,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 6429 frames
+      Peak usage frame count: [0-1.0 KB]: 7211 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]: 6428 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 7210 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

@@ -2,305 +2,305 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 3.2537543773651123,
-            "min": 3.2069151401519775,
-            "max": 3.2958173751831055,
-            "count": 33
+            "value": 3.1999590396881104,
+            "min": 3.1999006271362305,
+            "max": 3.241605281829834,
+            "count": 37
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 58411.3984375,
-            "min": 24713.4296875,
-            "max": 105466.15625,
-            "count": 33
+            "value": 66866.34375,
+            "min": 29757.73046875,
+            "max": 103708.4140625,
+            "count": 37
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 818.0,
-            "min": 447.0,
+            "value": 980.2,
+            "min": 354.26666666666665,
             "max": 999.0,
-            "count": 33
+            "count": 37
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19632.0,
-            "min": 1788.0,
-            "max": 31856.0,
-            "count": 33
+            "value": 19604.0,
+            "min": 8220.0,
+            "max": 28456.0,
+            "count": 37
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1209.357611408545,
-            "min": 1199.2393548497907,
-            "max": 1209.357611408545,
-            "count": 32
+            "value": 1211.9378862333965,
+            "min": 1205.1835371958437,
+            "max": 1215.6735285543373,
+            "count": 35
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 7256.14566845127,
-            "min": 2398.4787096995815,
-            "max": 16919.769407736774,
-            "count": 32
+            "value": 2423.875772466793,
+            "min": 2412.7680449870254,
+            "max": 26723.470354880505,
+            "count": 35
         },
         "SoccerTwos.Step.mean": {
-            "value": 329724.0,
-            "min": 9770.0,
-            "max": 329724.0,
-            "count": 33
+            "value": 699154.0,
+            "min": 339906.0,
+            "max": 699154.0,
+            "count": 37
         },
         "SoccerTwos.Step.sum": {
-            "value": 329724.0,
-            "min": 9770.0,
-            "max": 329724.0,
-            "count": 33
+            "value": 699154.0,
+            "min": 339906.0,
+            "max": 699154.0,
+            "count": 37
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": 0.0030621204059571028,
-            "min": -0.0008333418518304825,
-            "max": 0.07384230196475983,
-            "count": 33
+            "value": -0.004377217032015324,
+            "min": -0.011403935961425304,
+            "max": 0.00670193787664175,
+            "count": 37
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": 0.03674544394016266,
-            "min": -0.015000153332948685,
-            "max": 1.03379225730896,
-            "count": 33
+            "value": -0.043772172182798386,
+            "min": -0.21572968363761902,
+            "max": 0.09587319940328598,
+            "count": 37
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.0016769192880019546,
-            "min": -0.0017020993400365114,
-            "max": 0.07384181767702103,
-            "count": 33
+            "value": -0.0028003088664263487,
+            "min": -0.013163342140614986,
+            "max": 0.006617785431444645,
+            "count": 37
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 0.020123030990362167,
-            "min": -0.03063778765499592,
-            "max": 1.0337854623794556,
-            "count": 33
+            "value": -0.028003089129924774,
+            "min": -0.23477448523044586,
+            "max": 0.09730030596256256,
+            "count": 37
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 33
+            "count": 37
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 33
+            "count": 37
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.10413333773612976,
-            "min": -0.42857142857142855,
-            "max": 0.1590666671593984,
-            "count": 33
+            "value": -0.2,
+            "min": -0.5555200020472209,
+            "max": 0.3996470535502714,
+            "count": 37
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -1.2496000528335571,
-            "min": -6.0,
-            "max": 1.9088000059127808,
-            "count": 33
+            "value": -2.0,
+            "min": -9.0,
+            "max": 6.793999910354614,
+            "count": 37
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.10413333773612976,
-            "min": -0.42857142857142855,
-            "max": 0.1590666671593984,
-            "count": 33
+            "value": -0.2,
+            "min": -0.5555200020472209,
+            "max": 0.3996470535502714,
+            "count": 37
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -1.2496000528335571,
-            "min": -6.0,
-            "max": 1.9088000059127808,
-            "count": 33
+            "value": -2.0,
+            "min": -9.0,
+            "max": 6.793999910354614,
+            "count": 37
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 37
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 37
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.017120584277048087,
-            "min": 0.01184630231000483,
-            "max": 0.020048254150606227,
-            "count": 15
+            "value": 0.0159091107120427,
+            "min": 0.012636019413669904,
+            "max": 0.020098431833321228,
+            "count": 17
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.017120584277048087,
-            "min": 0.01184630231000483,
-            "max": 0.020048254150606227,
-            "count": 15
+            "value": 0.0159091107120427,
+            "min": 0.012636019413669904,
+            "max": 0.020098431833321228,
+            "count": 17
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.0025950087544818717,
-            "min": 0.0006825556454714387,
-            "max": 0.004943428281694651,
-            "count": 15
+            "value": 0.002516983779302488,
+            "min": 0.00014130498408727968,
+            "max": 0.0086365083232522,
+            "count": 17
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.0025950087544818717,
-            "min": 0.0006825556454714387,
-            "max": 0.004943428281694651,
-            "count": 15
+            "value": 0.002516983779302488,
+            "min": 0.00014130498408727968,
+            "max": 0.0086365083232522,
+            "count": 17
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.002597692298392455,
-            "min": 0.0006826190966724728,
-            "max": 0.0050204995010669036,
-            "count": 15
+            "value": 0.002624650854462137,
+            "min": 0.00014110098109085812,
+            "max": 0.008632027031853794,
+            "count": 17
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.002597692298392455,
-            "min": 0.0006826190966724728,
-            "max": 0.0050204995010669036,
-            "count": 15
+            "value": 0.002624650854462137,
+            "min": 0.00014110098109085812,
+            "max": 0.008632027031853794,
+            "count": 17
         },
         "SoccerTwos.Policy.LearningRate.mean": {
-            "value": 0.00019999999999999996,
-            "min": 0.00019999999999999996,
-            "max": 0.00020000000000000004,
-            "count": 15
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 17
         },
         "SoccerTwos.Policy.LearningRate.sum": {
-            "value": 0.00019999999999999996,
-            "min": 0.00019999999999999996,
-            "max": 0.00020000000000000004,
-            "count": 15
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 17
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.25,
             "min": 0.25,
             "max": 0.25,
-            "count": 15
+            "count": 17
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.25,
             "min": 0.25,
             "max": 0.25,
-            "count": 15
+            "count": 17
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.010000000000000002,
-            "min": 0.01,
+            "min": 0.010000000000000002,
             "max": 0.010000000000000002,
-            "count": 15
+            "count": 17
         },
         "SoccerTwos.Policy.Beta.sum": {
             "value": 0.010000000000000002,
-            "min": 0.01,
+            "min": 0.010000000000000002,
             "max": 0.010000000000000002,
-            "count": 15
+            "count": 17
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1683405461",
+        "start_time_seconds": "1683407536",
         "python_version": "3.9.16 | packaged by conda-forge | (main, Feb  1 2023, 21:38:11) \n[Clang 14.0.6 ]",
-        "command_line_arguments": "/Users/andreas.bjarlestam/mambaforge/envs/huggingface-rl-course/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics",
+        "command_line_arguments": "/Users/andreas.bjarlestam/mambaforge/envs/huggingface-rl-course/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --resume",
         "mlagents_version": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1683406974"
+        "end_time_seconds": "1683409217"
     },
-    "total": 1512.703789291,
+    "total": 1680.865004125,
     "count": 1,
-    "self": 0.1597869570000512,
+    "self": 0.12260970800002724,
     "children": {
         "run_training.setup": {
-            "total": 0.05548366699999985,
+            "total": 0.013448125000000033,
             "count": 1,
-            "self": 0.05548366699999985
+            "self": 0.013448125000000033
         },
         "TrainerController.start_learning": {
-            "total": 1512.4885186669999,
+            "total": 1680.728946292,
             "count": 1,
-            "self": 0.25970882700585207,
+            "self": 0.2918064929965567,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.2931211249999333,
-                    "count": 2,
-                    "self": 2.2931211249999333
+                    "total": 1.733552874999984,
+                    "count": 3,
+                    "self": 1.733552874999984
                 },
                 "TrainerController.advance": {
-                    "total": 1509.782210796994,
-                    "count": 21579,
-                    "self": 0.24726577001251826,
+                    "total": 1678.5335023400037,
+                    "count": 24247,
+                    "self": 0.28358365201415836,
                     "children": {
                         "env_step": {
-                            "total": 1238.8051764919874,
-                            "count": 21579,
-                            "self": 1195.3630238779756,
+                            "total": 1387.8335258989998,
+                            "count": 24247,
+                            "self": 1339.7047586980023,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 43.25285580400478,
-                                    "count": 21579,
-                                    "self": 1.2754701040110632,
+                                    "total": 47.923312614988625,
+                                    "count": 24247,
+                                    "self": 1.4153185770023171,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 41.97738569999372,
-                                            "count": 42860,
-                                            "self": 41.97738569999372
+                                            "total": 46.50799403798631,
+                                            "count": 48068,
+                                            "self": 46.50799403798631
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.1892968100068888,
-                                    "count": 21578,
+                                    "total": 0.20545458600886946,
+                                    "count": 24246,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1509.6495894130055,
-                                            "count": 21578,
+                                            "total": 1678.4846704740066,
+                                            "count": 24246,
                                             "is_parallel": true,
-                                            "self": 349.4384122730048,
+                                            "self": 380.76107760500213,
                                             "children": {
                                                 "steps_from_proto": {
-                                                    "total": 0.0037250000000343952,
-                                                    "count": 4,
+                                                    "total": 0.005257666000014982,
+                                                    "count": 6,
                                                     "is_parallel": true,
-                                                    "self": 0.0005595840002534658,
+                                                    "self": 0.0006387100000131429,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.0031654159997809295,
-                                                            "count": 16,
+                                                            "total": 0.004618956000001839,
+                                                            "count": 24,
                                                             "is_parallel": true,
-                                                            "self": 0.0031654159997809295
+                                                            "self": 0.004618956000001839
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1160.2074521400007,
-                                                    "count": 21578,
+                                                    "total": 1297.7183352030045,
+                                                    "count": 24246,
                                                     "is_parallel": true,
-                                                    "self": 3.0327681719870725,
+                                                    "self": 3.2725019259994497,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 20.090124248995796,
-                                                            "count": 21578,
+                                                            "total": 22.31964003499131,
+                                                            "count": 24246,
                                                             "is_parallel": true,
-                                                            "self": 20.090124248995796
+                                                            "self": 22.31964003499131
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1094.6483185990135,
-                                                            "count": 21578,
+                                                            "total": 1224.7218267430092,
+                                                            "count": 24246,
                                                             "is_parallel": true,
-                                                            "self": 1094.6483185990135
+                                                            "self": 1224.7218267430092
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 42.43624112000441,
-                                                            "count": 43156,
+                                                            "total": 47.40436649900448,
+                                                            "count": 48492,
                                                             "is_parallel": true,
-                                                            "self": 4.705739092995032,
+                                                            "self": 5.1485635459650325,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 37.73050202700938,
-                                                                    "count": 172624,
+                                                                    "total": 42.25580295303945,
+                                                                    "count": 193968,
                                                                     "is_parallel": true,
-                                                                    "self": 37.73050202700938
+                                                                    "self": 42.25580295303945
                                                                 }
                                                             }
                                                         }
@@ -313,24 +313,24 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 270.7297685349941,
-                            "count": 21578,
-                            "self": 2.1676305409926613,
+                            "total": 290.41639278898964,
+                            "count": 24246,
+                            "self": 2.2689823499720774,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 37.25934370100136,
-                                    "count": 21578,
-                                    "self": 37.25934370100136
+                                    "total": 40.91866668901776,
+                                    "count": 24246,
+                                    "self": 40.91866668901776
                                 },
                                 "_update_policy": {
-                                    "total": 231.30279429300006,
-                                    "count": 15,
-                                    "self": 29.242100787998396,
+                                    "total": 247.2287437499998,
+                                    "count": 17,
+                                    "self": 32.059548280997035,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 202.06069350500167,
-                                            "count": 462,
-                                            "self": 202.06069350500167
+                                            "total": 215.16919546900277,
+                                            "count": 510,
+                                            "self": 215.16919546900277
                                         }
                                     }
                                 }
@@ -339,19 +339,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 5.840001904289238e-07,
+                    "total": 5.839999630552484e-07,
                     "count": 1,
-                    "self": 5.840001904289238e-07
+                    "self": 5.839999630552484e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.15347733399994468,
+                    "total": 0.17008399999986068,
                     "count": 1,
-                    "self": 0.005591333999973358,
+                    "self": 0.001209707999805687,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.14788599999997132,
+                            "total": 0.168874292000055,
                             "count": 1,
-                            "self": 0.14788599999997132
+                            "self": 0.168874292000055
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,6 +1,6 @@
 {
     "SoccerTwos": {
-        "elo": 1212.4032246556544,
+        "elo": 1210.7004396795849,
         "checkpoints": [
             {
                 "steps": 331652,
@@ -10,15 +10,24 @@
                 "auxillary_file_paths": [
                     "results/SoccerTwos/SoccerTwos/SoccerTwos-331652.pt"
                 ]
+            },
+            {
+                "steps": 701120,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-701120.onnx",
+                "reward": 0.0,
+                "creation_time": 1683409217.594496,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-701120.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 331652,
+            "steps": 701120,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1683406974.434873,
+            "creation_time": 1683409217.594496,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-331652.pt"
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-701120.pt"
             ]
         }
     },