Update_agent

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6ac922a21f6419aeeb79564603e92a8c47ae84cc9ce6185659997e5b6e55389
+oid sha256:420a6c284a61845940bc2046a511e0d4c90599eaf072353160902fcc1de419f9
 size 886472

SoccerTwos/SoccerTwos-13499965.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5adfe997d89ec731e498773e785247e449e92ecd322aae45a727b5a84d2b1692
+size 886472

SoccerTwos/SoccerTwos-13499965.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d4b701dbfac5cb775c77591bb43629d46a2e2f811586c89fa89b489328ff053
+size 10303217

SoccerTwos/SoccerTwos-13999943.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d0fae37b49df2659138912e735ff133e9544d39a91fb142a7352ddd636f05fa
+size 886472

SoccerTwos/SoccerTwos-13999943.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:288197bdf59e72e4e6ed05eb17329f869828af6150a4fe37dee70e2785c97712
+size 10303217

SoccerTwos/SoccerTwos-14499998.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be91ab6e730ba7a8e3e241002ab9a6ca8823f73a0a33fc825b052fde7c1d8b0f
+size 886472

SoccerTwos/SoccerTwos-14499998.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0effbe706036bb9aa9a76aff7ef66e9d11d4d65f3cd8222c8a28bc70a0403a69
+size 10303217

SoccerTwos/SoccerTwos-14999958.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:420a6c284a61845940bc2046a511e0d4c90599eaf072353160902fcc1de419f9
+size 886472

SoccerTwos/SoccerTwos-14999958.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ede19bce1f48e5c239abcafb1440789a0e44fefbffeb443fead8de5117b0b7b
+size 10303217

SoccerTwos/SoccerTwos-15000116.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:420a6c284a61845940bc2046a511e0d4c90599eaf072353160902fcc1de419f9
+size 886472

SoccerTwos/SoccerTwos-15000116.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24b36b9b5e6622b8b76dcbd67915263bcc0e402ca47256ac66af2c1396b93f4a
+size 10303217

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda3347955b883fed4d1fa5ca1722187aec70d6589706dc8c24e66c27c984612
+oid sha256:24b36b9b5e6622b8b76dcbd67915263bcc0e402ca47256ac66af2c1396b93f4a
 size 10303217

SoccerTwos/events.out.tfevents.1691413447.d33d669e7b9d.14923.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01121f476f7c16cb62a07da2d8db0c30f001cd457ef835595843bd799bbba52c
+size 2056981

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.99, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.95, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 15000000, "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": 0.0002, "beta": 0.005, "epsilon": 0.2, "lambd": 0.99, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.975, "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": 15000000, "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

@@ -5,7 +5,7 @@ behaviors:
     hyperparameters:
       batch_size: 2048
       buffer_size: 20480
-      learning_rate: 0.0003
+      learning_rate: 0.0002
       beta: 0.005
       epsilon: 0.2
       lambd: 0.99
@@ -24,7 +24,7 @@ behaviors:
       deterministic: false
     reward_signals:
       extrinsic:
-        gamma: 0.95
+        gamma: 0.975
         strength: 1.0
         network_settings:
           normalize: false

run_logs/Player-0.log

@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/SoccerTwos_Data/Man
 Mono config path = '/content/ml-agents/training-envs-executables/SoccerTwos_Data/MonoBleedingEdge/etc'
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/SoccerTwos
-Unable to load player prefs
 Initialize engine version: 2021.3.14f1 (eee1884e7226)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/SoccerTwos_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.093 seconds
+- Completed reload, in  0.211 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -59,7 +56,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.662542 ms
+UnloadTime: 0.636160 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
@@ -68,7 +65,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 16672 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 37594 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.1 MB
@@ -184,22 +181,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 4
+  Peak main deferred allocation count 3
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 16673 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 37595 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 4.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 16673 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 37595 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
@@ -228,13 +225,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 16672 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 37594 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]: 16673 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 37595 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -246,16 +243,16 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 16673 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 37595 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]: 16672 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 37594 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
-      Peak Block count 2
-      Peak Allocated memory 4.3 MB
+      Peak Block count 1
+      Peak Allocated memory 4.0 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
@@ -264,13 +261,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 16673 frames
+      Peak usage frame count: [0-1.0 KB]: 37595 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]: 16672 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 37594 frames, [2.0 KB-4.0 KB]: 1 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 KB

run_logs/timers.json

@@ -2,201 +2,201 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 2.0170538425445557,
-            "min": 1.9972507953643799,
-            "max": 2.2256991863250732,
-            "count": 88
+            "value": 2.096771001815796,
+            "min": 1.7978801727294922,
+            "max": 2.198930501937866,
+            "count": 201
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 40405.62109375,
-            "min": 37537.67578125,
-            "max": 46557.78515625,
-            "count": 88
+            "value": 41599.9375,
+            "min": 690.385986328125,
+            "max": 47759.4921875,
+            "count": 201
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 42.0,
-            "min": 39.12,
-            "max": 68.18055555555556,
-            "count": 88
+            "value": 58.16470588235294,
+            "min": 10.0,
+            "max": 59.811764705882354,
+            "count": 201
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19320.0,
-            "min": 18824.0,
-            "max": 20548.0,
-            "count": 88
+            "value": 19776.0,
+            "min": 40.0,
+            "max": 20336.0,
+            "count": 201
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1498.7779997425816,
-            "min": 1471.804093027367,
-            "max": 1513.380500435241,
-            "count": 88
+            "value": 1554.956835449178,
+            "min": 1486.59631400373,
+            "max": 1554.956835449178,
+            "count": 201
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 344718.9399407938,
-            "min": 213823.54250999942,
-            "max": 371550.6815187331,
-            "count": 88
+            "value": 264342.6620263603,
+            "min": 3003.063497265889,
+            "max": 374218.4854370862,
+            "count": 201
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 201
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 201
         },
         "SoccerTwos.Step.mean": {
-            "value": 13379974.0,
-            "min": 12509994.0,
-            "max": 13379974.0,
-            "count": 88
+            "value": 14999958.0,
+            "min": 13009978.0,
+            "max": 14999958.0,
+            "count": 200
         },
         "SoccerTwos.Step.sum": {
-            "value": 13379974.0,
-            "min": 12509994.0,
-            "max": 13379974.0,
-            "count": 88
+            "value": 14999958.0,
+            "min": 13009978.0,
+            "max": 14999958.0,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": 0.02328161522746086,
-            "min": -0.07533109933137894,
-            "max": 0.06940919160842896,
-            "count": 88
+            "value": 0.043893054127693176,
+            "min": -0.09020467102527618,
+            "max": 0.07734177261590958,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": 5.401334762573242,
-            "min": -15.442874908447266,
-            "max": 14.36770248413086,
-            "count": 88
+            "value": 7.461819171905518,
+            "min": -19.213594436645508,
+            "max": 15.545696258544922,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.023491045460104942,
-            "min": -0.07633703947067261,
-            "max": 0.07690165936946869,
-            "count": 88
+            "value": 0.04128238558769226,
+            "min": -0.08795364946126938,
+            "max": 0.0766124352812767,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 5.449922561645508,
-            "min": -15.649093627929688,
-            "max": 15.9186429977417,
-            "count": 88
+            "value": 7.018005847930908,
+            "min": -18.734127044677734,
+            "max": 15.399099349975586,
+            "count": 200
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 88
+            "count": 200
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 88
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": 0.028268965667691725,
-            "min": -0.37212292857286405,
-            "max": 0.1393845412466261,
-            "count": 88
+            "value": 0.11723058854832369,
+            "min": -0.3401765263696232,
+            "max": 0.18128047151678411,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": 6.55840003490448,
-            "min": -76.28520035743713,
-            "max": 28.852600038051605,
-            "count": 88
+            "value": 19.929200053215027,
+            "min": -72.45760011672974,
+            "max": 39.10800004005432,
+            "count": 200
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": 0.028268965667691725,
-            "min": -0.37212292857286405,
-            "max": 0.1393845412466261,
-            "count": 88
+            "value": 0.11723058854832369,
+            "min": -0.3401765263696232,
+            "max": 0.18128047151678411,
+            "count": 200
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": 6.55840003490448,
-            "min": -76.28520035743713,
-            "max": 28.852600038051605,
-            "count": 88
-        },
-        "SoccerTwos.IsTraining.mean": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 88
-        },
-        "SoccerTwos.IsTraining.sum": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 88
+            "value": 19.929200053215027,
+            "min": -72.45760011672974,
+            "max": 39.10800004005432,
+            "count": 200
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.01801625022975107,
-            "min": 0.011879822385465862,
-            "max": 0.02180827030679211,
-            "count": 42
+            "value": 0.018280768686478648,
+            "min": 0.011735149780724896,
+            "max": 0.024575366786060236,
+            "count": 97
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.01801625022975107,
-            "min": 0.011879822385465862,
-            "max": 0.02180827030679211,
-            "count": 42
+            "value": 0.018280768686478648,
+            "min": 0.011735149780724896,
+            "max": 0.024575366786060236,
+            "count": 97
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.08463414534926414,
-            "min": 0.07863207459449768,
-            "max": 0.09561808233459791,
-            "count": 42
+            "value": 0.1402090256412824,
+            "min": 0.13842538744211197,
+            "max": 0.16264882385730745,
+            "count": 97
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.08463414534926414,
-            "min": 0.07863207459449768,
-            "max": 0.09561808233459791,
-            "count": 42
+            "value": 0.1402090256412824,
+            "min": 0.13842538744211197,
+            "max": 0.16264882385730745,
+            "count": 97
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.08579889833927154,
-            "min": 0.07998814011613528,
-            "max": 0.0967168872555097,
-            "count": 42
+            "value": 0.14100217719872793,
+            "min": 0.1402094433705012,
+            "max": 0.16492244303226472,
+            "count": 97
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.08579889833927154,
-            "min": 0.07998814011613528,
-            "max": 0.0967168872555097,
-            "count": 42
+            "value": 0.14100217719872793,
+            "min": 0.1402094433705012,
+            "max": 0.16492244303226472,
+            "count": 97
         },
         "SoccerTwos.Policy.LearningRate.mean": {
-            "value": 0.0003,
-            "min": 0.0003,
-            "max": 0.0003,
-            "count": 42
+            "value": 0.00019999999999999996,
+            "min": 0.00019999999999999996,
+            "max": 0.00019999999999999996,
+            "count": 97
         },
         "SoccerTwos.Policy.LearningRate.sum": {
-            "value": 0.0003,
-            "min": 0.0003,
-            "max": 0.0003,
-            "count": 42
+            "value": 0.00019999999999999996,
+            "min": 0.00019999999999999996,
+            "max": 0.00019999999999999996,
+            "count": 97
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.20000000000000007,
             "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 42
+            "count": 97
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.20000000000000007,
             "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 42
+            "count": 97
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.005000000000000001,
             "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 42
+            "count": 97
         },
         "SoccerTwos.Policy.Beta.sum": {
             "value": 0.005000000000000001,
             "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 42
+            "count": 97
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1691410106",
+        "start_time_seconds": "1691413445",
         "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume --torch-device=cpu",
         "mlagents_version": "0.31.0.dev0",
@@ -204,59 +204,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1691413365"
+        "end_time_seconds": "1691420891"
     },
-    "total": 3259.086342517,
+    "total": 7446.493744302001,
     "count": 1,
-    "self": 0.7392523739999888,
+    "self": 0.44090754500211915,
     "children": {
         "run_training.setup": {
-            "total": 0.0587807919999932,
+            "total": 0.05116394600008789,
             "count": 1,
-            "self": 0.0587807919999932
+            "self": 0.05116394600008789
         },
         "TrainerController.start_learning": {
-            "total": 3258.288309351,
+            "total": 7446.001672810999,
             "count": 1,
-            "self": 1.7680477739754679,
+            "self": 4.463491247934144,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.445354537000469,
-                    "count": 5,
-                    "self": 2.445354537000469
+                    "total": 2.2937364919985157,
+                    "count": 10,
+                    "self": 2.2937364919985157
                 },
                 "TrainerController.advance": {
-                    "total": 3254.074117151024,
-                    "count": 62738,
-                    "self": 1.533715553028287,
+                    "total": 7439.116317394068,
+                    "count": 142012,
+                    "self": 3.6368457870757993,
                     "children": {
                         "env_step": {
-                            "total": 1273.310644220974,
-                            "count": 62738,
-                            "self": 1062.8171075409816,
+                            "total": 2941.015872404006,
+                            "count": 142012,
+                            "self": 2456.025975177389,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 209.46814199198388,
-                                    "count": 62738,
-                                    "self": 7.206732080007555,
+                                    "total": 482.48543693276815,
+                                    "count": 142012,
+                                    "self": 17.11533814368886,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 202.26140991197633,
-                                            "count": 111152,
-                                            "self": 202.26140991197633
+                                            "total": 465.3700987890793,
+                                            "count": 250632,
+                                            "self": 465.3700987890793
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 1.0253946880084754,
-                                    "count": 62737,
+                                    "total": 2.504460293849206,
+                                    "count": 142012,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 3254.072856265011,
-                                            "count": 62737,
+                                            "total": 7436.180982305729,
+                                            "count": 142012,
                                             "is_parallel": true,
-                                            "self": 2366.7271369250225,
+                                            "self": 5390.057720905652,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -265,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.00983552799999643,
+                                                            "total": 0.00443643999960841,
                                                             "count": 2,
                                                             "is_parallel": true,
-                                                            "self": 0.00724677799996698,
+                                                            "self": 0.0011098709992438671,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0025887500000294494,
+                                                                    "total": 0.003326569000364543,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0025887500000294494
+                                                                    "self": 0.003326569000364543
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04980938699998205,
+                                                            "total": 0.048430476000248746,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0012535100000832244,
+                                                            "self": 0.0010615390001476044,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0007586599999740429,
+                                                                    "total": 0.0007993300000634918,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0007586599999740429
+                                                                    "self": 0.0007993300000634918
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.044380516999979136,
+                                                                    "total": 0.04133742700014409,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.044380516999979136
+                                                                    "self": 0.04133742700014409
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0034166999999456493,
+                                                                    "total": 0.00523217999989356,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.000673259999871334,
+                                                                    "self": 0.0005823099995723169,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0027434400000743153,
+                                                                            "total": 0.004649870000321243,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0027434400000743153
+                                                                            "self": 0.004649870000321243
                                                                         }
                                                                     }
                                                                 }
@@ -315,48 +315,48 @@
                                                     }
                                                 },
                                                 "steps_from_proto": {
-                                                    "total": 0.008660468999892146,
-                                                    "count": 8,
+                                                    "total": 0.01876272900335607,
+                                                    "count": 18,
                                                     "is_parallel": true,
-                                                    "self": 0.0016107209999631777,
+                                                    "self": 0.003684774000703328,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.007049747999928968,
-                                                            "count": 32,
+                                                            "total": 0.015077955002652743,
+                                                            "count": 72,
                                                             "is_parallel": true,
-                                                            "self": 0.007049747999928968
+                                                            "self": 0.015077955002652743
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 887.3370588709888,
-                                                    "count": 62736,
+                                                    "total": 2046.104498671074,
+                                                    "count": 142011,
                                                     "is_parallel": true,
-                                                    "self": 55.339384674010375,
+                                                    "self": 125.091241453154,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 27.926248527957114,
-                                                            "count": 62736,
+                                                            "total": 65.50758502101417,
+                                                            "count": 142011,
                                                             "is_parallel": true,
-                                                            "self": 27.926248527957114
+                                                            "self": 65.50758502101417
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 637.3668925890175,
-                                                            "count": 62736,
+                                                            "total": 1475.5032075824838,
+                                                            "count": 142011,
                                                             "is_parallel": true,
-                                                            "self": 637.3668925890175
+                                                            "self": 1475.5032075824838
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 166.70453308000378,
-                                                            "count": 125472,
+                                                            "total": 380.002464614422,
+                                                            "count": 284022,
                                                             "is_parallel": true,
-                                                            "self": 30.377168298046172,
+                                                            "self": 69.75164025852473,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 136.3273647819576,
-                                                                    "count": 501888,
+                                                                    "total": 310.2508243558973,
+                                                                    "count": 1136088,
                                                                     "is_parallel": true,
-                                                                    "self": 136.3273647819576
+                                                                    "self": 310.2508243558973
                                                                 }
                                                             }
                                                         }
@@ -369,31 +369,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 1979.2297573770218,
-                            "count": 62737,
-                            "self": 12.382054871022092,
+                            "total": 4494.463599202985,
+                            "count": 142012,
+                            "self": 29.215439991813582,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 311.74384310800116,
-                                    "count": 62737,
-                                    "self": 311.2617028940011,
+                                    "total": 712.2678581821747,
+                                    "count": 142012,
+                                    "self": 711.6323160651764,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.4821402140000828,
-                                            "count": 1,
-                                            "self": 0.4821402140000828
+                                            "total": 0.6355421169982947,
+                                            "count": 5,
+                                            "self": 0.6355421169982947
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 1655.1038593979986,
-                                    "count": 43,
-                                    "self": 144.60367413699691,
+                                    "total": 3752.980301028997,
+                                    "count": 97,
+                                    "self": 324.84123214594683,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 1510.5001852610017,
-                                            "count": 1290,
-                                            "self": 1510.5001852610017
+                                            "total": 3428.13906888305,
+                                            "count": 2910,
+                                            "self": 3428.13906888305
                                         }
                                     }
                                 }
@@ -402,19 +402,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.0690000635804608e-06,
+                    "total": 6.299997039604932e-07,
                     "count": 1,
-                    "self": 1.0690000635804608e-06
+                    "self": 6.299997039604932e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.0007888199997978518,
+                    "total": 0.12812704699899768,
                     "count": 1,
-                    "self": 3.7939999856462236e-05,
+                    "self": 0.0025897599989548326,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.0007508799999413895,
+                            "total": 0.12553728700004285,
                             "count": 1,
-                            "self": 0.0007508799999413895
+                            "self": 0.12553728700004285
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,59 +2,59 @@
     "SoccerTwos": {
         "checkpoints": [
             {
-                "steps": 11499962,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-11499962.onnx",
+                "steps": 13499965,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-13499965.onnx",
                 "reward": 0.0,
-                "creation_time": 1691334164.167952,
+                "creation_time": 1691415288.943044,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-11499962.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-13499965.pt"
                 ]
             },
             {
-                "steps": 11999948,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-11999948.onnx",
+                "steps": 13999943,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-13999943.onnx",
                 "reward": 0.0,
-                "creation_time": 1691336061.3931055,
+                "creation_time": 1691417137.7242517,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-11999948.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-13999943.pt"
                 ]
             },
             {
-                "steps": 12499998,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-12499998.onnx",
+                "steps": 14499998,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-14499998.onnx",
                 "reward": 0.0,
-                "creation_time": 1691337965.0599864,
+                "creation_time": 1691418971.7557998,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-12499998.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-14499998.pt"
                 ]
             },
             {
-                "steps": 12500022,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-12500022.onnx",
+                "steps": 14999958,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-14999958.onnx",
                 "reward": 0.0,
-                "creation_time": 1691337965.2721767,
+                "creation_time": 1691420890.8887775,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-12500022.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-14999958.pt"
                 ]
             },
             {
-                "steps": 12999992,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-12999992.onnx",
+                "steps": 15000116,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-15000116.onnx",
                 "reward": 0.0,
-                "creation_time": 1691411948.116917,
+                "creation_time": 1691420891.0595102,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-12999992.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-15000116.pt"
                 ]
             }
         ],
-        "elo": 1501.5317486329445,
+        "elo": 1554.3576125423003,
         "final_checkpoint": {
-            "steps": 12500022,
+            "steps": 15000116,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1691337965.2721767,
+            "creation_time": 1691420891.0595102,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-12500022.pt"
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-15000116.pt"
             ]
         }
     },