New_agent

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77d8fa1c483924b28248ed69c6c6a9c2156086ef46f1893584811cd194e535fb
+oid sha256:b5e010abd1e594ae079014e5569924f82504f6822ad205260aea55eea97c4236
 size 886472

SoccerTwos/SoccerTwos-499284.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5e010abd1e594ae079014e5569924f82504f6822ad205260aea55eea97c4236
+size 886472

SoccerTwos/SoccerTwos-499284.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce80f2c35b55a6fca9da6613555831b9748d5a8792efcb56d241befbf2b36f3f
+size 10303217

SoccerTwos/SoccerTwos-500284.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5e010abd1e594ae079014e5569924f82504f6822ad205260aea55eea97c4236
+size 886472

SoccerTwos/SoccerTwos-500284.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7049a4887f915b7c957a317732bf0ea67d1e108d6de08e6e66d4e8263c1f15b4
+size 10303217

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b389f4e61a8548581d3f6c2a198dabc6c0a186f13faf4910d4d8e6b601b70aab
-size 10304625
+oid sha256:7049a4887f915b7c957a317732bf0ea67d1e108d6de08e6e66d4e8263c1f15b4
+size 10303217

SoccerTwos/events.out.tfevents.1690831907.28f97f24b86c.6029.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e571eb21c59b8022d0b91c4b891d0c3211617184e735be0ae9c5bcf78f6b04b
+size 378422

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.00055, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "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": 2250000, "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": null}, "debug": false}
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0009, "beta": 0.005, "epsilon": 0.2, "lambd": 0.8, "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": 500000, "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": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": "cpu"}, "debug": false}

configuration.yaml

@@ -5,10 +5,10 @@ behaviors:
     hyperparameters:
       batch_size: 2048
       buffer_size: 20480
-      learning_rate: 0.00055
+      learning_rate: 0.0009
       beta: 0.005
       epsilon: 0.2
-      lambd: 0.95
+      lambd: 0.8
       num_epoch: 3
       learning_rate_schedule: constant
       beta_schedule: constant
@@ -37,7 +37,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 2250000
+    max_steps: 500000
     time_horizon: 1000
     summary_freq: 10000
     threaded: false
@@ -72,11 +72,11 @@ checkpoint_settings:
   run_id: SoccerTwos
   initialize_from: null
   load_model: false
-  resume: true
+  resume: false
   force: false
   train_model: false
   inference: false
   results_dir: results
 torch_settings:
-  device: null
+  device: cpu
 debug: false

run_logs/Player-0.log

@@ -31,7 +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  0.119 seconds
+- Completed reload, in  0.125 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)
@@ -56,7 +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: 0.941001 ms
+UnloadTime: 0.926396 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
@@ -257,17 +257,12 @@ TOO LONG
 TOO LONG
 TOO LONG
 TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
 Setting up 1 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]: 9764 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 9775 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
@@ -295,7 +290,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 0]
       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 10]
       Initial Block Size 32.0 KB
@@ -383,22 +378,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 5
+  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]: 9765 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 9776 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 4.6 MB
+      Peak Allocated memory 4.7 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 9765 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 9776 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.6 MB
+      Peak Allocated memory 17.5 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -427,13 +422,13 @@ 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]: 9764 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 9775 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]: 9765 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 9776 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -445,13 +440,13 @@ 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]: 9765 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 9776 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]: 9764 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 9775 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.5 MB
@@ -463,13 +458,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 9765 frames
+      Peak usage frame count: [0-1.0 KB]: 9776 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]: 9764 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 9775 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

@@ -2,75 +2,75 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 3.151453971862793,
-            "min": 3.127227544784546,
-            "max": 3.1760921478271484,
+            "value": 3.2572760581970215,
+            "min": 3.220968008041382,
+            "max": 3.2958123683929443,
             "count": 50
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 64037.54296875,
-            "min": 20419.759765625,
-            "max": 111017.0,
+            "value": 64207.42578125,
+            "min": 22911.15234375,
+            "max": 119298.5859375,
             "count": 50
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 638.5,
-            "min": 478.72727272727275,
+            "value": 724.5714285714286,
+            "min": 470.3,
             "max": 999.0,
             "count": 50
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 20432.0,
-            "min": 11828.0,
-            "max": 27064.0,
+            "value": 20288.0,
+            "min": 16864.0,
+            "max": 23884.0,
             "count": 50
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1174.2121493977888,
-            "min": 1165.2629482200864,
-            "max": 1181.0289495804443,
-            "count": 47
+            "value": 1203.9032315327422,
+            "min": 1199.9971506578554,
+            "max": 1214.9892240181,
+            "count": 43
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 9393.69719518231,
-            "min": 2336.271198475225,
-            "max": 16434.89980380847,
-            "count": 47
+            "value": 7223.419389196453,
+            "min": 2408.436526094936,
+            "max": 14568.006544586702,
+            "count": 43
         },
         "SoccerTwos.Step.mean": {
-            "value": 2249936.0,
-            "min": 1759929.0,
-            "max": 2249936.0,
+            "value": 499284.0,
+            "min": 9082.0,
+            "max": 499284.0,
             "count": 50
         },
         "SoccerTwos.Step.sum": {
-            "value": 2249936.0,
-            "min": 1759929.0,
-            "max": 2249936.0,
+            "value": 499284.0,
+            "min": 9082.0,
+            "max": 499284.0,
             "count": 50
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": 0.0031177180353552103,
-            "min": -0.00878502894192934,
-            "max": 0.0031177180353552103,
+            "value": -0.0017586464527994394,
+            "min": -0.0022823000326752663,
+            "max": 0.12102693319320679,
             "count": 50
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": 0.049883488565683365,
-            "min": -0.15813052654266357,
-            "max": 0.049883488565683365,
+            "value": -0.02462105080485344,
+            "min": -0.02462105080485344,
+            "max": 1.694377064704895,
             "count": 50
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.004119338467717171,
-            "min": -0.008890403434634209,
-            "max": 0.004119338467717171,
+            "value": -0.0017902880208566785,
+            "min": -0.0023909122683107853,
+            "max": 0.12102709710597992,
             "count": 50
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 0.06590941548347473,
-            "min": -0.16002726554870605,
-            "max": 0.06590941548347473,
+            "value": -0.025064032524824142,
+            "min": -0.025064032524824142,
+            "max": 1.6943793296813965,
             "count": 50
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
@@ -86,27 +86,27 @@
             "count": 50
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.0622749999165535,
-            "min": -0.6666666666666666,
-            "max": 0.2682857151542391,
+            "value": -0.16605714389256068,
+            "min": -0.4166666666666667,
+            "max": 0.3248400012652079,
             "count": 50
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -0.996399998664856,
-            "min": -10.0,
-            "max": 3.7560000121593475,
+            "value": -2.3248000144958496,
+            "min": -5.0,
+            "max": 4.872600018978119,
             "count": 50
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.0622749999165535,
-            "min": -0.6666666666666666,
-            "max": 0.2682857151542391,
+            "value": -0.16605714389256068,
+            "min": -0.4166666666666667,
+            "max": 0.3248400012652079,
             "count": 50
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -0.996399998664856,
-            "min": -10.0,
-            "max": 3.7560000121593475,
+            "value": -2.3248000144958496,
+            "min": -5.0,
+            "max": 4.872600018978119,
             "count": 50
         },
         "SoccerTwos.IsTraining.mean": {
@@ -122,141 +122,141 @@
             "count": 50
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.014403438732309344,
-            "min": 0.010229992038633402,
-            "max": 0.019984069629572332,
+            "value": 0.018052726998575963,
+            "min": 0.011876711369647333,
+            "max": 0.022964291064999996,
             "count": 23
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.014403438732309344,
-            "min": 0.010229992038633402,
-            "max": 0.019984069629572332,
+            "value": 0.018052726998575963,
+            "min": 0.011876711369647333,
+            "max": 0.022964291064999996,
             "count": 23
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.003362401939618091,
-            "min": 0.00013077333521020287,
-            "max": 0.0043448854548235735,
+            "value": 0.0005519891194126104,
+            "min": 4.7260880364774494e-05,
+            "max": 0.0013224981385671223,
             "count": 23
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.003362401939618091,
-            "min": 0.00013077333521020287,
-            "max": 0.0043448854548235735,
+            "value": 0.0005519891194126104,
+            "min": 4.7260880364774494e-05,
+            "max": 0.0013224981385671223,
             "count": 23
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.0034127482950376967,
-            "min": 0.00013574239558996246,
-            "max": 0.0044469629181548955,
+            "value": 0.0005516268897432989,
+            "min": 4.71035714175135e-05,
+            "max": 0.0013219986848222712,
             "count": 23
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.0034127482950376967,
-            "min": 0.00013574239558996246,
-            "max": 0.0044469629181548955,
+            "value": 0.0005516268897432989,
+            "min": 4.71035714175135e-05,
+            "max": 0.0013219986848222712,
             "count": 23
         },
         "SoccerTwos.Policy.LearningRate.mean": {
-            "value": 0.0005499999999999999,
-            "min": 0.0005499999999999999,
-            "max": 0.00055,
+            "value": 0.0009000000000000003,
+            "min": 0.0009000000000000003,
+            "max": 0.0009000000000000003,
             "count": 23
         },
         "SoccerTwos.Policy.LearningRate.sum": {
-            "value": 0.0005499999999999999,
-            "min": 0.0005499999999999999,
-            "max": 0.00055,
+            "value": 0.0009000000000000003,
+            "min": 0.0009000000000000003,
+            "max": 0.0009000000000000003,
             "count": 23
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.20000000000000007,
-            "min": 0.2,
+            "min": 0.20000000000000007,
             "max": 0.20000000000000007,
             "count": 23
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.20000000000000007,
-            "min": 0.2,
+            "min": 0.20000000000000007,
             "max": 0.20000000000000007,
             "count": 23
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.005000000000000001,
-            "min": 0.005,
+            "min": 0.005000000000000001,
             "max": 0.005000000000000001,
             "count": 23
         },
         "SoccerTwos.Policy.Beta.sum": {
             "value": 0.005000000000000001,
-            "min": 0.005,
+            "min": 0.005000000000000001,
             "max": 0.005000000000000001,
             "count": 23
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1690804445",
+        "start_time_seconds": "1690831906",
         "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
-        "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",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --torch-device=cpu",
         "mlagents_version": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1690805540"
+        "end_time_seconds": "1690833772"
     },
-    "total": 1095.4753349929997,
+    "total": 1866.9491970109998,
     "count": 1,
-    "self": 0.38822889600032795,
+    "self": 0.492338197999743,
     "children": {
         "run_training.setup": {
-            "total": 0.03129372500006866,
+            "total": 0.042752336000148716,
             "count": 1,
-            "self": 0.03129372500006866
+            "self": 0.042752336000148716
         },
         "TrainerController.start_learning": {
-            "total": 1095.0558123719993,
+            "total": 1866.414106477,
             "count": 1,
-            "self": 0.7822017468861304,
+            "self": 1.2027670320169364,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 5.9570331720005925,
-                    "count": 4,
-                    "self": 5.9570331720005925
+                    "total": 1.6527223570001297,
+                    "count": 3,
+                    "self": 1.6527223570001297
                 },
                 "TrainerController.advance": {
-                    "total": 1088.1120374991133,
-                    "count": 32835,
-                    "self": 0.8069334171414084,
+                    "total": 1863.3430414389832,
+                    "count": 32815,
+                    "self": 1.2149952469203527,
                     "children": {
                         "env_step": {
-                            "total": 882.2106680920333,
-                            "count": 32835,
-                            "self": 699.2274848741445,
+                            "total": 1053.6878785300441,
+                            "count": 32815,
+                            "self": 883.5911888210437,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 182.54068637993714,
-                                    "count": 32835,
-                                    "self": 5.318234501108236,
+                                    "total": 169.33696699094617,
+                                    "count": 32815,
+                                    "self": 7.717916546916285,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 177.2224518788289,
-                                            "count": 65094,
-                                            "self": 177.2224518788289
+                                            "total": 161.61905044402988,
+                                            "count": 65172,
+                                            "self": 161.61905044402988
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.44249683795169403,
-                                    "count": 32835,
+                                    "total": 0.7597227180542632,
+                                    "count": 32815,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1092.3884063230407,
-                                            "count": 32835,
+                                            "total": 1860.5536074640086,
+                                            "count": 32815,
                                             "is_parallel": true,
-                                            "self": 498.6851029291065,
+                                            "self": 1121.993401950994,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -265,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.00451230700036831,
+                                                            "total": 0.005697713000017757,
                                                             "count": 2,
                                                             "is_parallel": true,
-                                                            "self": 0.0009606280018488178,
+                                                            "self": 0.0014901889999237028,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.003551678998519492,
+                                                                    "total": 0.004207524000094054,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.003551678998519492
+                                                                    "self": 0.004207524000094054
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.07229993299915805,
+                                                            "total": 0.05979127399996287,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.001307245998759754,
+                                                            "self": 0.0013965059999918594,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0007551199996669311,
+                                                                    "total": 0.0007554509998044523,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0007551199996669311
+                                                                    "self": 0.0007554509998044523
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.06639388900021004,
+                                                                    "total": 0.04217132100006893,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.06639388900021004
+                                                                    "self": 0.04217132100006893
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0038436780005213222,
+                                                                    "total": 0.015467996000097628,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0006122100003267406,
+                                                                    "self": 0.0008975469997949403,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0032314680001945817,
+                                                                            "total": 0.014570449000302688,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0032314680001945817
+                                                                            "self": 0.014570449000302688
                                                                         }
                                                                     }
                                                                 }
@@ -314,53 +314,53 @@
                                                         }
                                                     }
                                                 },
-                                                "steps_from_proto": {
-                                                    "total": 0.007196964998911426,
-                                                    "count": 6,
-                                                    "is_parallel": true,
-                                                    "self": 0.0013209269991421024,
-                                                    "children": {
-                                                        "_process_rank_one_or_two_observation": {
-                                                            "total": 0.0058760379997693235,
-                                                            "count": 24,
-                                                            "is_parallel": true,
-                                                            "self": 0.0058760379997693235
-                                                        }
-                                                    }
-                                                },
                                                 "UnityEnvironment.step": {
-                                                    "total": 593.6961064289353,
-                                                    "count": 32834,
+                                                    "total": 738.5539974580145,
+                                                    "count": 32814,
                                                     "is_parallel": true,
-                                                    "self": 36.63282161472853,
+                                                    "self": 44.08710844193433,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 23.15455671015843,
-                                                            "count": 32834,
+                                                            "total": 22.847336305016825,
+                                                            "count": 32814,
                                                             "is_parallel": true,
-                                                            "self": 23.15455671015843
+                                                            "self": 22.847336305016825
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 416.26482188099453,
-                                                            "count": 32834,
+                                                            "total": 529.7087338390243,
+                                                            "count": 32814,
                                                             "is_parallel": true,
-                                                            "self": 416.26482188099453
+                                                            "self": 529.7087338390243
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 117.64390622305382,
-                                                            "count": 65668,
+                                                            "total": 141.91081887203904,
+                                                            "count": 65628,
                                                             "is_parallel": true,
-                                                            "self": 19.087857136731145,
+                                                            "self": 24.357934929080784,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 98.55604908632267,
-                                                                    "count": 262672,
+                                                                    "total": 117.55288394295826,
+                                                                    "count": 262512,
                                                                     "is_parallel": true,
-                                                                    "self": 98.55604908632267
+                                                                    "self": 117.55288394295826
                                                                 }
                                                             }
                                                         }
                                                     }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.006208055000115564,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 0.0010749359998953878,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.0051331190002201765,
+                                                            "count": 16,
+                                                            "is_parallel": true,
+                                                            "self": 0.0051331190002201765
+                                                        }
+                                                    }
                                                 }
                                             }
                                         }
@@ -369,31 +369,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 205.09443598993857,
-                            "count": 32835,
-                            "self": 6.719612829871949,
+                            "total": 808.4401676620187,
+                            "count": 32815,
+                            "self": 10.116855313013275,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 50.66163941806735,
-                                    "count": 32835,
-                                    "self": 50.458558852067654,
+                                    "total": 119.80808097500494,
+                                    "count": 32815,
+                                    "self": 119.57963060100519,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.2030805659996986,
+                                            "total": 0.228450373999749,
                                             "count": 1,
-                                            "self": 0.2030805659996986
+                                            "self": 0.228450373999749
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 147.71318374199927,
+                                    "total": 678.5152313740005,
                                     "count": 23,
-                                    "self": 103.30691072398713,
+                                    "self": 133.32459764600367,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 44.40627301801214,
-                                            "count": 693,
-                                            "self": 44.40627301801214
+                                            "total": 545.1906337279968,
+                                            "count": 690,
+                                            "self": 545.1906337279968
                                         }
                                     }
                                 }
@@ -402,19 +402,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.93999492493458e-07,
+                    "total": 1.0369999472459313e-06,
                     "count": 1,
-                    "self": 9.93999492493458e-07
+                    "self": 1.0369999472459313e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.20453895999980887,
+                    "total": 0.2155746119997275,
                     "count": 1,
-                    "self": 0.0014291139996203128,
+                    "self": 0.0015714729997853283,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.20310984600018855,
+                            "total": 0.21400313899994217,
                             "count": 1,
-                            "self": 0.20310984600018855
+                            "self": 0.21400313899994217
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,59 +2,32 @@
     "SoccerTwos": {
         "checkpoints": [
             {
-                "steps": 1001682,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-1001682.onnx",
+                "steps": 499284,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-499284.onnx",
                 "reward": 0.0,
-                "creation_time": 1690802601.1996052,
+                "creation_time": 1690833772.087084,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-1001682.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-499284.pt"
                 ]
             },
             {
-                "steps": 1499348,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-1499348.onnx",
+                "steps": 500284,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-500284.onnx",
                 "reward": 0.0,
-                "creation_time": 1690803798.3821926,
+                "creation_time": 1690833772.489504,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-1499348.pt"
-                ]
-            },
-            {
-                "steps": 1751370,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-1751370.onnx",
-                "reward": 0.0,
-                "creation_time": 1690804337.4087615,
-                "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-1751370.pt"
-                ]
-            },
-            {
-                "steps": 1999160,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-1999160.onnx",
-                "reward": 0.0,
-                "creation_time": 1690804996.4361818,
-                "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-1999160.pt"
-                ]
-            },
-            {
-                "steps": 2251936,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-2251936.onnx",
-                "reward": 0.0,
-                "creation_time": 1690805540.2085571,
-                "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-2251936.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-500284.pt"
                 ]
             }
         ],
-        "elo": 1175.6017727005901,
+        "elo": 1203.5182823775556,
         "final_checkpoint": {
-            "steps": 2251936,
+            "steps": 500284,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1690805540.2085571,
+            "creation_time": 1690833772.489504,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-2251936.pt"
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-500284.pt"
             ]
         }
     },