Update_agent

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:420a6c284a61845940bc2046a511e0d4c90599eaf072353160902fcc1de419f9
+oid sha256:217e01281f063efc8f65086ef02ad407c0041bda38fea68f78076a65f3aca1af
 size 886472

SoccerTwos/SoccerTwos-15499926.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad487edae01cfa8eed71fa2499b966566892eb41d02d5af08e2e463eb5099d7d
+size 886472

SoccerTwos/SoccerTwos-15499926.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66fc2c511676e1e6baba1e49d0c8166195773f99c5ef57baca049c9f4506548d
+size 10303217

SoccerTwos/SoccerTwos-15999985.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:217e01281f063efc8f65086ef02ad407c0041bda38fea68f78076a65f3aca1af
+size 886472

SoccerTwos/SoccerTwos-15999985.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcbff4532d2264d8a5bf792d274e10f65b34650d8e6f8d1d8c502cf63402f97c
+size 10303217

SoccerTwos/SoccerTwos-16000076.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:217e01281f063efc8f65086ef02ad407c0041bda38fea68f78076a65f3aca1af
+size 886472

SoccerTwos/SoccerTwos-16000076.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b32ffeadc0cd3cc9d64ee854f0b7fb573564ab47ecf0057b2036af1bc9a4076
+size 10303217

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24b36b9b5e6622b8b76dcbd67915263bcc0e402ca47256ac66af2c1396b93f4a
+oid sha256:8b32ffeadc0cd3cc9d64ee854f0b7fb573564ab47ecf0057b2036af1bc9a4076
 size 10303217

SoccerTwos/events.out.tfevents.1691420993.d33d669e7b9d.45218.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17db0f950409a6d930d4a5b3c7493e4696fcd8c580546ccf2b79e1b0289471b3
+size 1028851

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0002, "beta": 0.005, "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}
+{"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": 16000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 60000, "team_change": 225000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.25, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": "cpu"}, "debug": false}

configuration.yaml

@@ -37,7 +37,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 15000000
+    max_steps: 16000000
     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  0.211 seconds
+- Completed reload, in  0.072 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: 0.636160 ms
+UnloadTime: 0.581921 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
@@ -65,7 +65,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 37594 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 18825 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
@@ -187,16 +187,16 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 37595 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 18826 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 4.6 MB
+      Peak Allocated memory 5.0 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 37595 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18826 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.6 MB
+      Peak Allocated memory 17.2 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -225,13 +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]: 37594 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18825 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]: 37595 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 18826 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -243,16 +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]: 37595 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 18826 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]: 37594 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 18825 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
@@ -261,13 +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]: 37595 frames
+      Peak usage frame count: [0-1.0 KB]: 18826 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]: 37594 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18825 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": 2.096771001815796,
-            "min": 1.7978801727294922,
-            "max": 2.198930501937866,
-            "count": 201
+            "value": 2.009509325027466,
+            "min": 1.9547885656356812,
+            "max": 2.115744113922119,
+            "count": 100
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 41599.9375,
-            "min": 690.385986328125,
-            "max": 47759.4921875,
-            "count": 201
+            "value": 38711.1875,
+            "min": 35846.48828125,
+            "max": 45286.48828125,
+            "count": 100
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 58.16470588235294,
-            "min": 10.0,
-            "max": 59.811764705882354,
-            "count": 201
+            "value": 61.31645569620253,
+            "min": 45.728971962616825,
+            "max": 84.2542372881356,
+            "count": 100
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19776.0,
-            "min": 40.0,
-            "max": 20336.0,
-            "count": 201
+            "value": 19376.0,
+            "min": 18868.0,
+            "max": 20624.0,
+            "count": 100
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1554.956835449178,
-            "min": 1486.59631400373,
-            "max": 1554.956835449178,
-            "count": 201
+            "value": 1533.6912155307195,
+            "min": 1520.5147887283385,
+            "max": 1575.1452576090742,
+            "count": 100
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "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
+            "value": 242323.2120538537,
+            "min": 182996.85854448657,
+            "max": 334580.1672081369,
+            "count": 100
         },
         "SoccerTwos.Step.mean": {
-            "value": 14999958.0,
-            "min": 13009978.0,
-            "max": 14999958.0,
-            "count": 200
+            "value": 15999985.0,
+            "min": 15009934.0,
+            "max": 15999985.0,
+            "count": 100
         },
         "SoccerTwos.Step.sum": {
-            "value": 14999958.0,
-            "min": 13009978.0,
-            "max": 14999958.0,
-            "count": 200
+            "value": 15999985.0,
+            "min": 15009934.0,
+            "max": 15999985.0,
+            "count": 100
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": 0.043893054127693176,
-            "min": -0.09020467102527618,
-            "max": 0.07734177261590958,
-            "count": 200
+            "value": -0.03876939043402672,
+            "min": -0.11050329357385635,
+            "max": 0.07117976993322372,
+            "count": 100
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": 7.461819171905518,
-            "min": -19.213594436645508,
-            "max": 15.545696258544922,
-            "count": 200
+            "value": -6.164333343505859,
+            "min": -17.238513946533203,
+            "max": 12.812358856201172,
+            "count": 100
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.04128238558769226,
-            "min": -0.08795364946126938,
-            "max": 0.0766124352812767,
-            "count": 200
+            "value": -0.03973289951682091,
+            "min": -0.11041993647813797,
+            "max": 0.06990461051464081,
+            "count": 100
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 7.018005847930908,
-            "min": -18.734127044677734,
-            "max": 15.399099349975586,
-            "count": 200
+            "value": -6.317531108856201,
+            "min": -17.225509643554688,
+            "max": 12.582830429077148,
+            "count": 100
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 200
+            "count": 100
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 200
+            "count": 100
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": 0.11723058854832369,
-            "min": -0.3401765263696232,
-            "max": 0.18128047151678411,
-            "count": 200
+            "value": -0.14481006253440426,
+            "min": -0.31689342228989853,
+            "max": 0.2551560954349797,
+            "count": 100
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": 19.929200053215027,
-            "min": -72.45760011672974,
-            "max": 39.10800004005432,
-            "count": 200
+            "value": -23.024799942970276,
+            "min": -48.167800188064575,
+            "max": 43.98160004615784,
+            "count": 100
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": 0.11723058854832369,
-            "min": -0.3401765263696232,
-            "max": 0.18128047151678411,
-            "count": 200
+            "value": -0.14481006253440426,
+            "min": -0.31689342228989853,
+            "max": 0.2551560954349797,
+            "count": 100
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": 19.929200053215027,
-            "min": -72.45760011672974,
-            "max": 39.10800004005432,
-            "count": 200
+            "value": -23.024799942970276,
+            "min": -48.167800188064575,
+            "max": 43.98160004615784,
+            "count": 100
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 100
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 100
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.018280768686478648,
-            "min": 0.011735149780724896,
-            "max": 0.024575366786060236,
-            "count": 97
+            "value": 0.018470443135205034,
+            "min": 0.012020956303119116,
+            "max": 0.02259021265587459,
+            "count": 48
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.018280768686478648,
-            "min": 0.011735149780724896,
-            "max": 0.024575366786060236,
-            "count": 97
+            "value": 0.018470443135205034,
+            "min": 0.012020956303119116,
+            "max": 0.02259021265587459,
+            "count": 48
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.1402090256412824,
-            "min": 0.13842538744211197,
-            "max": 0.16264882385730745,
-            "count": 97
+            "value": 0.1388648788134257,
+            "min": 0.12739655300974845,
+            "max": 0.16285738994677862,
+            "count": 48
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.1402090256412824,
-            "min": 0.13842538744211197,
-            "max": 0.16264882385730745,
-            "count": 97
+            "value": 0.1388648788134257,
+            "min": 0.12739655300974845,
+            "max": 0.16285738994677862,
+            "count": 48
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.14100217719872793,
-            "min": 0.1402094433705012,
-            "max": 0.16492244303226472,
-            "count": 97
+            "value": 0.14071978032588958,
+            "min": 0.1279634507993857,
+            "max": 0.16412917921940487,
+            "count": 48
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.14100217719872793,
-            "min": 0.1402094433705012,
-            "max": 0.16492244303226472,
-            "count": 97
+            "value": 0.14071978032588958,
+            "min": 0.1279634507993857,
+            "max": 0.16412917921940487,
+            "count": 48
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.00019999999999999996,
             "min": 0.00019999999999999996,
             "max": 0.00019999999999999996,
-            "count": 97
+            "count": 48
         },
         "SoccerTwos.Policy.LearningRate.sum": {
             "value": 0.00019999999999999996,
             "min": 0.00019999999999999996,
             "max": 0.00019999999999999996,
-            "count": 97
+            "count": 48
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.20000000000000007,
             "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 97
+            "count": 48
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.20000000000000007,
             "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 97
+            "count": 48
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.005000000000000001,
             "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 97
+            "count": 48
         },
         "SoccerTwos.Policy.Beta.sum": {
             "value": 0.005000000000000001,
             "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 97
+            "count": 48
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1691413445",
+        "start_time_seconds": "1691420992",
         "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": "1691420891"
+        "end_time_seconds": "1691424712"
     },
-    "total": 7446.493744302001,
+    "total": 3719.9456217080005,
     "count": 1,
-    "self": 0.44090754500211915,
+    "self": 0.3856991590000689,
     "children": {
         "run_training.setup": {
-            "total": 0.05116394600008789,
+            "total": 0.035546506000173395,
             "count": 1,
-            "self": 0.05116394600008789
+            "self": 0.035546506000173395
         },
         "TrainerController.start_learning": {
-            "total": 7446.001672810999,
+            "total": 3719.5243760430003,
             "count": 1,
-            "self": 4.463491247934144,
+            "self": 2.178103340216694,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.2937364919985157,
-                    "count": 10,
-                    "self": 2.2937364919985157
+                    "total": 0.904719957999987,
+                    "count": 6,
+                    "self": 0.904719957999987
                 },
                 "TrainerController.advance": {
-                    "total": 7439.116317394068,
-                    "count": 142012,
-                    "self": 3.6368457870757993,
+                    "total": 3716.3129400657836,
+                    "count": 69533,
+                    "self": 1.8816615488121897,
                     "children": {
                         "env_step": {
-                            "total": 2941.015872404006,
-                            "count": 142012,
-                            "self": 2456.025975177389,
+                            "total": 1475.2068245499086,
+                            "count": 69533,
+                            "self": 1228.3319889637041,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 482.48543693276815,
-                                    "count": 142012,
-                                    "self": 17.11533814368886,
+                                    "total": 245.6641817652926,
+                                    "count": 69533,
+                                    "self": 9.218874684012917,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 465.3700987890793,
-                                            "count": 250632,
-                                            "self": 465.3700987890793
+                                            "total": 236.44530708127968,
+                                            "count": 125504,
+                                            "self": 236.44530708127968
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 2.504460293849206,
-                                    "count": 142012,
+                                    "total": 1.2106538209118298,
+                                    "count": 69533,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 7436.180982305729,
-                                            "count": 142012,
+                                            "total": 3715.0637501149486,
+                                            "count": 69533,
                                             "is_parallel": true,
-                                            "self": 5390.057720905652,
+                                            "self": 2702.538275396695,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -265,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.00443643999960841,
+                                                            "total": 0.0020812500006286427,
                                                             "count": 2,
                                                             "is_parallel": true,
-                                                            "self": 0.0011098709992438671,
+                                                            "self": 0.0004852399997616885,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.003326569000364543,
+                                                                    "total": 0.0015960100008669542,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.003326569000364543
+                                                                    "self": 0.0015960100008669542
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.048430476000248746,
+                                                            "total": 0.03561966600136657,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0010615390001476044,
+                                                            "self": 0.0009461900026508374,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0007993300000634918,
+                                                                    "total": 0.0005976399988867342,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0007993300000634918
+                                                                    "self": 0.0005976399988867342
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04133742700014409,
+                                                                    "total": 0.031276177000108873,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04133742700014409
+                                                                    "self": 0.031276177000108873
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.00523217999989356,
+                                                                    "total": 0.0027996589997201227,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005823099995723169,
+                                                                    "self": 0.0005430500004877103,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.004649870000321243,
+                                                                            "total": 0.0022566089992324123,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.004649870000321243
+                                                                            "self": 0.0022566089992324123
                                                                         }
                                                                     }
                                                                 }
@@ -315,48 +315,48 @@
                                                     }
                                                 },
                                                 "steps_from_proto": {
-                                                    "total": 0.01876272900335607,
-                                                    "count": 18,
+                                                    "total": 0.009731358997669304,
+                                                    "count": 10,
                                                     "is_parallel": true,
-                                                    "self": 0.003684774000703328,
+                                                    "self": 0.001728736995573854,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.015077955002652743,
-                                                            "count": 72,
+                                                            "total": 0.00800262200209545,
+                                                            "count": 40,
                                                             "is_parallel": true,
-                                                            "self": 0.015077955002652743
+                                                            "self": 0.00800262200209545
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 2046.104498671074,
-                                                    "count": 142011,
+                                                    "total": 1012.5157433592558,
+                                                    "count": 69532,
                                                     "is_parallel": true,
-                                                    "self": 125.091241453154,
+                                                    "self": 62.15438385401103,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 65.50758502101417,
-                                                            "count": 142011,
+                                                            "total": 33.16059458309974,
+                                                            "count": 69532,
                                                             "is_parallel": true,
-                                                            "self": 65.50758502101417
+                                                            "self": 33.16059458309974
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1475.5032075824838,
-                                                            "count": 142011,
+                                                            "total": 730.5288143470443,
+                                                            "count": 69532,
                                                             "is_parallel": true,
-                                                            "self": 1475.5032075824838
+                                                            "self": 730.5288143470443
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 380.002464614422,
-                                                            "count": 284022,
+                                                            "total": 186.6719505751007,
+                                                            "count": 139064,
                                                             "is_parallel": true,
-                                                            "self": 69.75164025852473,
+                                                            "self": 34.07769961905433,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 310.2508243558973,
-                                                                    "count": 1136088,
+                                                                    "total": 152.59425095604638,
+                                                                    "count": 556256,
                                                                     "is_parallel": true,
-                                                                    "self": 310.2508243558973
+                                                                    "self": 152.59425095604638
                                                                 }
                                                             }
                                                         }
@@ -369,31 +369,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 4494.463599202985,
-                            "count": 142012,
-                            "self": 29.215439991813582,
+                            "total": 2239.224453967063,
+                            "count": 69533,
+                            "self": 14.596125622361797,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 712.2678581821747,
-                                    "count": 142012,
-                                    "self": 711.6323160651764,
+                                    "total": 346.02428062869694,
+                                    "count": 69533,
+                                    "self": 345.7213318546965,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.6355421169982947,
-                                            "count": 5,
-                                            "self": 0.6355421169982947
+                                            "total": 0.3029487740004697,
+                                            "count": 2,
+                                            "self": 0.3029487740004697
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 3752.980301028997,
-                                    "count": 97,
-                                    "self": 324.84123214594683,
+                                    "total": 1878.604047716004,
+                                    "count": 48,
+                                    "self": 165.35072026198577,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 3428.13906888305,
-                                            "count": 2910,
-                                            "self": 3428.13906888305
+                                            "total": 1713.2533274540183,
+                                            "count": 1440,
+                                            "self": 1713.2533274540183
                                         }
                                     }
                                 }
@@ -402,19 +402,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 6.299997039604932e-07,
+                    "total": 7.399994501611218e-07,
                     "count": 1,
-                    "self": 6.299997039604932e-07
+                    "self": 7.399994501611218e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.12812704699899768,
+                    "total": 0.12861193900062062,
                     "count": 1,
-                    "self": 0.0025897599989548326,
+                    "self": 0.001239719000295736,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.12553728700004285,
+                            "total": 0.1273722200003249,
                             "count": 1,
-                            "self": 0.12553728700004285
+                            "self": 0.1273722200003249
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,59 +2,59 @@
     "SoccerTwos": {
         "checkpoints": [
             {
-                "steps": 13499965,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-13499965.onnx",
+                "steps": 14999958,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-14999958.onnx",
                 "reward": 0.0,
-                "creation_time": 1691415288.943044,
+                "creation_time": 1691420890.8887775,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-13499965.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-14999958.pt"
                 ]
             },
             {
-                "steps": 13999943,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-13999943.onnx",
+                "steps": 15000116,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-15000116.onnx",
                 "reward": 0.0,
-                "creation_time": 1691417137.7242517,
+                "creation_time": 1691420891.0595102,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-13999943.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-15000116.pt"
                 ]
             },
             {
-                "steps": 14499998,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-14499998.onnx",
+                "steps": 15499926,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-15499926.onnx",
                 "reward": 0.0,
-                "creation_time": 1691418971.7557998,
+                "creation_time": 1691422879.2576034,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-14499998.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-15499926.pt"
                 ]
             },
             {
-                "steps": 14999958,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-14999958.onnx",
+                "steps": 15999985,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-15999985.onnx",
                 "reward": 0.0,
-                "creation_time": 1691420890.8887775,
+                "creation_time": 1691424711.922073,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-14999958.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-15999985.pt"
                 ]
             },
             {
-                "steps": 15000116,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-15000116.onnx",
+                "steps": 16000076,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-16000076.onnx",
                 "reward": 0.0,
-                "creation_time": 1691420891.0595102,
+                "creation_time": 1691424712.242151,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-15000116.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-16000076.pt"
                 ]
             }
         ],
-        "elo": 1554.3576125423003,
+        "elo": 1523.730691385121,
         "final_checkpoint": {
-            "steps": 15000116,
+            "steps": 16000076,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1691420891.0595102,
+            "creation_time": 1691424712.242151,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-15000116.pt"
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-16000076.pt"
             ]
         }
     },