Update_agent

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12b0b78dd84a0436d20a429fff85138c1f8da81d6517618febac2005cc84e8cc
+oid sha256:20d3878c5013dd8b7cf408da01694c5d55de342e095fb4c2f7848374a30edc50
 size 886472

SoccerTwos/SoccerTwos-1999130.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20d3878c5013dd8b7cf408da01694c5d55de342e095fb4c2f7848374a30edc50
+size 886472

SoccerTwos/SoccerTwos-1999130.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8306e7bf36b882f7afff7ef93535599742faa37afa0e3be86cf88a19ec241f3
+size 10303217

SoccerTwos/SoccerTwos-2001130.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20d3878c5013dd8b7cf408da01694c5d55de342e095fb4c2f7848374a30edc50
+size 886472

SoccerTwos/SoccerTwos-2001130.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:755e50be4a79eb85f19e25501d2d3594bc16c6f442b1cef96b017cb3227ffb36
+size 10303217

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2de3b07e6becfdecdbce3e95025209593ba7a46dfd7b9f32e5a9666dd73a19fe
+oid sha256:755e50be4a79eb85f19e25501d2d3594bc16c6f442b1cef96b017cb3227ffb36
 size 10303217

SoccerTwos/events.out.tfevents.1690838278.28f97f24b86c.31821.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:966501e6ce4c77e0f6afb4a833b9922e8c5f7555013cafe46bc39ee30fa67b51
+size 384959

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0006, "beta": 0.005, "epsilon": 0.2, "lambd": 0.92, "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": 1500000, "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": 0.0005, "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": 2000000, "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

@@ -5,10 +5,10 @@ behaviors:
     hyperparameters:
       batch_size: 2048
       buffer_size: 20480
-      learning_rate: 0.0006
+      learning_rate: 0.0005
       beta: 0.005
       epsilon: 0.2
-      lambd: 0.92
+      lambd: 0.95
       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: 1500000
+    max_steps: 2000000
     time_horizon: 1000
     summary_freq: 10000
     threaded: 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  0.138 seconds
+- Completed reload, in  0.137 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: 1.149206 ms
+UnloadTime: 1.061747 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
@@ -255,41 +255,12 @@ TOO LONG
 TOO LONG
 TOO LONG
 TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-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]: 9704 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 9673 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
@@ -411,17 +382,17 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 9705 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 9674 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 20.6 MB
-      Peak Large allocation bytes 16.0 MB
+      Peak Allocated memory 4.6 MB
+      Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 9705 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 9674 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 1.6 MB
-      Peak Large allocation bytes 0 B
+      Peak Allocated memory 17.6 MB
+      Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
   Used Block Count 1
@@ -449,13 +420,13 @@ 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]: 9704 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 9673 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]: 9705 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 9674 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -467,16 +438,16 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 9705 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 9674 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]: 9704 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 9673 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
-      Peak Block count 1
-      Peak Allocated memory 4.0 MB
+      Peak Block count 2
+      Peak Allocated memory 4.5 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
@@ -485,13 +456,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 9705 frames
+      Peak usage frame count: [0-1.0 KB]: 9674 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]: 9704 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 9673 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": 3.22896146774292,
-            "min": 3.1848373413085938,
-            "max": 3.2397873401641846,
+            "value": 3.1842167377471924,
+            "min": 3.172684907913208,
+            "max": 3.249568462371826,
             "count": 50
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 46910.3515625,
-            "min": 17658.828125,
-            "max": 102906.75,
+            "value": 35459.4375,
+            "min": 13283.650390625,
+            "max": 117639.375,
             "count": 50
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 878.8333333333334,
-            "min": 580.0,
+            "value": 688.0,
+            "min": 341.46153846153845,
             "max": 999.0,
             "count": 50
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 21092.0,
-            "min": 9680.0,
-            "max": 28356.0,
+            "value": 22016.0,
+            "min": 4124.0,
+            "max": 31968.0,
             "count": 50
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1207.9839607543527,
-            "min": 1203.361182298351,
-            "max": 1209.4159941625653,
-            "count": 37
+            "value": 1226.0866013136713,
+            "min": 1202.3735835901539,
+            "max": 1226.0866013136713,
+            "count": 46
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 2415.9679215087053,
-            "min": 2406.722364596702,
-            "max": 9656.165338551153,
-            "count": 37
+            "value": 7356.519607882027,
+            "min": 2404.7471671803078,
+            "max": 22042.38445482544,
+            "count": 46
         },
         "SoccerTwos.Step.mean": {
-            "value": 1499626.0,
-            "min": 1009782.0,
-            "max": 1499626.0,
+            "value": 1999130.0,
+            "min": 1509307.0,
+            "max": 1999130.0,
             "count": 50
         },
         "SoccerTwos.Step.sum": {
-            "value": 1499626.0,
-            "min": 1009782.0,
-            "max": 1499626.0,
+            "value": 1999130.0,
+            "min": 1509307.0,
+            "max": 1999130.0,
             "count": 50
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.0005232731928117573,
-            "min": -0.004119817167520523,
-            "max": 0.0015827578026801348,
+            "value": 0.0016364417970180511,
+            "min": -0.004181301221251488,
+            "max": 0.008756794035434723,
             "count": 50
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -0.006279278080910444,
-            "min": -0.0516546294093132,
-            "max": 0.016616934910416603,
+            "value": 0.02618306875228882,
+            "min": -0.0664612427353859,
+            "max": 0.157622292637825,
             "count": 50
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 2.5139981516986154e-05,
-            "min": -0.0048939441330730915,
-            "max": 0.001756390556693077,
+            "value": 0.0002816212363541126,
+            "min": -0.0045310077257454395,
+            "max": 0.01224028505384922,
             "count": 50
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 0.00030167977092787623,
-            "min": -0.05872733145952225,
-            "max": 0.01756390556693077,
+            "value": 0.004505939781665802,
+            "min": -0.07003718614578247,
+            "max": 0.17136399447917938,
             "count": 50
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
@@ -86,27 +86,27 @@
             "count": 50
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.16666666666666666,
-            "min": -0.4,
-            "max": 0.1904666709403197,
+            "value": -0.03152499347925186,
+            "min": -0.42857142857142855,
+            "max": 0.45002222061157227,
             "count": 50
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -2.0,
-            "min": -4.0,
-            "max": 2.2856000512838364,
+            "value": -0.5043998956680298,
+            "min": -6.0,
+            "max": 8.1003999710083,
             "count": 50
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.16666666666666666,
-            "min": -0.4,
-            "max": 0.1904666709403197,
+            "value": -0.03152499347925186,
+            "min": -0.42857142857142855,
+            "max": 0.45002222061157227,
             "count": 50
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -2.0,
-            "min": -4.0,
-            "max": 2.2856000512838364,
+            "value": -0.5043998956680298,
+            "min": -6.0,
+            "max": 8.1003999710083,
             "count": 50
         },
         "SoccerTwos.IsTraining.mean": {
@@ -122,81 +122,81 @@
             "count": 50
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.016666618620123093,
-            "min": 0.013956846692599357,
-            "max": 0.022629022784531116,
-            "count": 23
+            "value": 0.017224992097665866,
+            "min": 0.013165214379445057,
+            "max": 0.021765073745821914,
+            "count": 22
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.016666618620123093,
-            "min": 0.013956846692599357,
-            "max": 0.022629022784531116,
-            "count": 23
+            "value": 0.017224992097665866,
+            "min": 0.013165214379445057,
+            "max": 0.021765073745821914,
+            "count": 22
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.0004101419082265541,
-            "min": 6.887182792070234e-07,
-            "max": 0.001591083847392255,
-            "count": 23
+            "value": 0.0023239689956729612,
+            "min": 0.0005247537120643149,
+            "max": 0.006923159894843896,
+            "count": 22
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.0004101419082265541,
-            "min": 6.887182792070234e-07,
-            "max": 0.001591083847392255,
-            "count": 23
+            "value": 0.0023239689956729612,
+            "min": 0.0005247537120643149,
+            "max": 0.006923159894843896,
+            "count": 22
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.0004095457172904086,
-            "min": 6.219582786570754e-07,
-            "max": 0.0015867490273637648,
-            "count": 23
+            "value": 0.002343843465981384,
+            "min": 0.0005249925727791075,
+            "max": 0.007085357047617436,
+            "count": 22
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.0004095457172904086,
-            "min": 6.219582786570754e-07,
-            "max": 0.0015867490273637648,
-            "count": 23
+            "value": 0.002343843465981384,
+            "min": 0.0005249925727791075,
+            "max": 0.007085357047617436,
+            "count": 22
         },
         "SoccerTwos.Policy.LearningRate.mean": {
-            "value": 0.0006,
-            "min": 0.0006,
-            "max": 0.0006,
-            "count": 23
+            "value": 0.0005000000000000001,
+            "min": 0.0005,
+            "max": 0.0005000000000000001,
+            "count": 22
         },
         "SoccerTwos.Policy.LearningRate.sum": {
-            "value": 0.0006,
-            "min": 0.0006,
-            "max": 0.0006,
-            "count": 23
+            "value": 0.0005000000000000001,
+            "min": 0.0005,
+            "max": 0.0005000000000000001,
+            "count": 22
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.20000000000000007,
-            "min": 0.20000000000000004,
+            "min": 0.2,
             "max": 0.20000000000000007,
-            "count": 23
+            "count": 22
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.20000000000000007,
-            "min": 0.20000000000000004,
+            "min": 0.2,
             "max": 0.20000000000000007,
-            "count": 23
+            "count": 22
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.005000000000000001,
-            "min": 0.005000000000000001,
+            "min": 0.005,
             "max": 0.005000000000000001,
-            "count": 23
+            "count": 22
         },
         "SoccerTwos.Policy.Beta.sum": {
             "value": 0.005000000000000001,
-            "min": 0.005000000000000001,
+            "min": 0.005,
             "max": 0.005000000000000001,
-            "count": 23
+            "count": 22
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1690836134",
+        "start_time_seconds": "1690838276",
         "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 --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": "1690838130"
+        "end_time_seconds": "1690840210"
     },
-    "total": 1996.5656753400008,
+    "total": 1933.9327643760007,
     "count": 1,
-    "self": 0.5412798930010467,
+    "self": 0.4902367780014174,
     "children": {
         "run_training.setup": {
-            "total": 0.060030644000107714,
+            "total": 0.060607506000451394,
             "count": 1,
-            "self": 0.060030644000107714
+            "self": 0.060607506000451394
         },
         "TrainerController.start_learning": {
-            "total": 1995.9643648029996,
+            "total": 1933.3819200919988,
             "count": 1,
-            "self": 1.315962397002295,
+            "self": 1.3161826378791375,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.08804731500004,
+                    "total": 2.0475889189992813,
                     "count": 4,
-                    "self": 2.08804731500004
+                    "self": 2.0475889189992813
                 },
                 "TrainerController.advance": {
-                    "total": 1992.333410817998,
-                    "count": 32576,
-                    "self": 1.3532669141413862,
+                    "total": 1929.7939666371203,
+                    "count": 32520,
+                    "self": 1.3229786641668397,
                     "children": {
                         "env_step": {
-                            "total": 1143.4442700788622,
-                            "count": 32576,
-                            "self": 962.7638915999123,
+                            "total": 1111.4364407127541,
+                            "count": 32520,
+                            "self": 933.357528601251,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 179.8672459990703,
-                                    "count": 32576,
-                                    "self": 7.80844156814328,
+                                    "total": 177.2854299587716,
+                                    "count": 32520,
+                                    "self": 8.542072947703673,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 172.058804430927,
-                                            "count": 64698,
-                                            "self": 172.058804430927
+                                            "total": 168.74335701106793,
+                                            "count": 64494,
+                                            "self": 168.74335701106793
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.8131324798796413,
-                                    "count": 32576,
+                                    "total": 0.7934821527314853,
+                                    "count": 32520,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1980.834241586098,
-                                            "count": 32576,
+                                            "total": 1922.9118322439936,
+                                            "count": 32520,
                                             "is_parallel": true,
-                                            "self": 1182.166430001218,
+                                            "self": 1147.965107933036,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -265,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.005761311000242131,
+                                                            "total": 0.006658627000433626,
                                                             "count": 2,
                                                             "is_parallel": true,
-                                                            "self": 0.0013010019993089372,
+                                                            "self": 0.001168770000731456,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.004460309000933194,
+                                                                    "total": 0.0054898569997021696,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.004460309000933194
+                                                                    "self": 0.0054898569997021696
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.08242809900002612,
+                                                            "total": 0.08002122800007783,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0013541799980885116,
+                                                            "self": 0.0013706099998671561,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0010495550004634424,
+                                                                    "total": 0.0009310750001532142,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0010495550004634424
+                                                                    "self": 0.0009310750001532142
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.0756327950002742,
+                                                                    "total": 0.07334866499968484,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0756327950002742
+                                                                    "self": 0.07334866499968484
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.004391569001199969,
+                                                                    "total": 0.004370878000372613,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.000847820002491062,
+                                                                    "self": 0.0007474649992218474,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0035437489987089066,
+                                                                            "total": 0.003623413001150766,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0035437489987089066
+                                                                            "self": 0.003623413001150766
                                                                         }
                                                                     }
                                                                 }
@@ -315,48 +315,48 @@
                                                     }
                                                 },
                                                 "steps_from_proto": {
-                                                    "total": 0.009897961000206124,
+                                                    "total": 0.010676853999029845,
                                                     "count": 6,
                                                     "is_parallel": true,
-                                                    "self": 0.0017937970005732495,
+                                                    "self": 0.0018945339979836717,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.008104163999632874,
+                                                            "total": 0.008782320001046173,
                                                             "count": 24,
                                                             "is_parallel": true,
-                                                            "self": 0.008104163999632874
+                                                            "self": 0.008782320001046173
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 798.6579136238797,
-                                                    "count": 32575,
+                                                    "total": 774.9360474569585,
+                                                    "count": 32519,
                                                     "is_parallel": true,
-                                                    "self": 47.85686024690767,
+                                                    "self": 46.491318513307306,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 24.062977560040963,
-                                                            "count": 32575,
+                                                            "total": 23.494726218955293,
+                                                            "count": 32519,
                                                             "is_parallel": true,
-                                                            "self": 24.062977560040963
+                                                            "self": 23.494726218955293
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 570.5423945099328,
-                                                            "count": 32575,
+                                                            "total": 556.1550727349577,
+                                                            "count": 32519,
                                                             "is_parallel": true,
-                                                            "self": 570.5423945099328
+                                                            "self": 556.1550727349577
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 156.19568130699827,
-                                                            "count": 65150,
+                                                            "total": 148.7949299897382,
+                                                            "count": 65038,
                                                             "is_parallel": true,
-                                                            "self": 26.6652478429005,
+                                                            "self": 25.85352793439506,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 129.53043346409777,
-                                                                    "count": 260600,
+                                                                    "total": 122.94140205534313,
+                                                                    "count": 260152,
                                                                     "is_parallel": true,
-                                                                    "self": 129.53043346409777
+                                                                    "self": 122.94140205534313
                                                                 }
                                                             }
                                                         }
@@ -369,31 +369,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 847.5358738249943,
-                            "count": 32576,
-                            "self": 11.022426634062867,
+                            "total": 817.0345472601994,
+                            "count": 32520,
+                            "self": 10.883385765314415,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 125.11756927492934,
-                                    "count": 32576,
-                                    "self": 124.59364989992991,
+                                    "total": 124.86339521088667,
+                                    "count": 32520,
+                                    "self": 124.61784183288728,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.5239193749994229,
+                                            "total": 0.2455533779993857,
                                             "count": 1,
-                                            "self": 0.5239193749994229
+                                            "self": 0.2455533779993857
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 711.3958779160021,
-                                    "count": 23,
-                                    "self": 131.06789364600354,
+                                    "total": 681.2877662839983,
+                                    "count": 22,
+                                    "self": 123.35581107800499,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 580.3279842699985,
-                                            "count": 699,
-                                            "self": 580.3279842699985
+                                            "total": 557.9319552059933,
+                                            "count": 672,
+                                            "self": 557.9319552059933
                                         }
                                     }
                                 }
@@ -402,19 +402,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.0889998520724475e-06,
+                    "total": 1.1310003174003214e-06,
                     "count": 1,
-                    "self": 1.0889998520724475e-06
+                    "self": 1.1310003174003214e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.22694318399953772,
+                    "total": 0.22418076699977973,
                     "count": 1,
-                    "self": 0.0023119159995985683,
+                    "self": 0.0019517669988999842,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.22463126799993915,
+                            "total": 0.22222900000087975,
                             "count": 1,
-                            "self": 0.22463126799993915
+                            "self": 0.22222900000087975
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,24 +1,6 @@
 {
     "SoccerTwos": {
         "checkpoints": [
-            {
-                "steps": 999580,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-999580.onnx",
-                "reward": 0.0,
-                "creation_time": 1690835902.663581,
-                "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-999580.pt"
-                ]
-            },
-            {
-                "steps": 1001580,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-1001580.onnx",
-                "reward": 0.0,
-                "creation_time": 1690835903.2777994,
-                "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-1001580.pt"
-                ]
-            },
             {
                 "steps": 1001580,
                 "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-1001580.onnx",
@@ -45,16 +27,34 @@
                 "auxillary_file_paths": [
                     "results/SoccerTwos/SoccerTwos/SoccerTwos-1500626.pt"
                 ]
+            },
+            {
+                "steps": 1999130,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-1999130.onnx",
+                "reward": 0.0,
+                "creation_time": 1690840209.2941182,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-1999130.pt"
+                ]
+            },
+            {
+                "steps": 2001130,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-2001130.onnx",
+                "reward": 0.0,
+                "creation_time": 1690840209.9085782,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-2001130.pt"
+                ]
             }
         ],
-        "elo": 1207.9839607543527,
+        "elo": 1227.0763100205886,
         "final_checkpoint": {
-            "steps": 1500626,
+            "steps": 2001130,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1690838130.059794,
+            "creation_time": 1690840209.9085782,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-1500626.pt"
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-2001130.pt"
             ]
         }
     },