Update_agent

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b526c8841b20151630e8b40735bf1ddce903eb72b787e5f9b2de1e53bbf6756
+oid sha256:2dac551666aa18fcafdec2a45f3055471376db9e465d0165a11fc83b03d6d465
 size 886472

SoccerTwos/SoccerTwos-2999941.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b36e983a5b5e62594b50b02782d398e7eebd86bd938fc9f44d38c39f06211fe
+size 886472

SoccerTwos/SoccerTwos-2999941.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5ab1c05c07f66861b6f69dbb1476fc194582d2ed54bba614836b14eb02ba1a
+size 10303217

SoccerTwos/SoccerTwos-3499730.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dac551666aa18fcafdec2a45f3055471376db9e465d0165a11fc83b03d6d465
+size 886472

SoccerTwos/SoccerTwos-3499730.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52c085c3825e89f110cafab6aeaf5aaa970aa2261cd3152102d58abae85e1675
+size 10303217

SoccerTwos/SoccerTwos-3501730.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dac551666aa18fcafdec2a45f3055471376db9e465d0165a11fc83b03d6d465
+size 886472

SoccerTwos/SoccerTwos-3501730.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d8c8eec76e3b80c69c550e11e1d09eb6f7d1aadba86f97dacb3d1a4ebe9e7b
+size 10303217

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff0f020a959057f6252cd46dd9108f3f32a0b37db38eb734f931d443a0de7d16
+oid sha256:69d8c8eec76e3b80c69c550e11e1d09eb6f7d1aadba86f97dacb3d1a4ebe9e7b
 size 10303217

SoccerTwos/events.out.tfevents.1690875390.93ce20cc1c4b.2018.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bcdea80c35c839f77ffc0f14094e4d0689052acdc6c68140ec517d0e810eabc
+size 771106

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.00045, "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": 0.9, "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": 2750000, "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": 0.0004, "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": 0.925, "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": 3500000, "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: 0.00045
+      learning_rate: 0.0004
       beta: 0.005
       epsilon: 0.2
       lambd: 0.99
@@ -24,7 +24,7 @@ behaviors:
       deterministic: false
     reward_signals:
       extrinsic:
-        gamma: 0.9
+        gamma: 0.925
         strength: 1.0
         network_settings:
           normalize: false
@@ -37,7 +37,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 2750000
+    max_steps: 3500000
     time_horizon: 1000
     summary_freq: 10000
     threaded: false

run_logs/Player-0.log

@@ -2,6 +2,9 @@ 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
@@ -31,7 +34,7 @@ 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  0.143 seconds
+- Completed reload, in  0.165 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 +59,7 @@ 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: 1.108713 ms
+UnloadTime: 1.580958 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
@@ -258,21 +261,12 @@ 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
 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]: 14429 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 14511 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
@@ -388,22 +382,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 3
+  Peak main deferred allocation count 4
     [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]: 14430 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 14512 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 4.7 MB
+      Peak Allocated memory 4.9 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 14430 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 14512 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.5 MB
+      Peak Allocated memory 17.3 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -432,13 +426,13 @@ 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]: 14429 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 14511 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]: 14430 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 14512 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -450,16 +444,16 @@ 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]: 14430 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 14512 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]: 14429 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 14511 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
-      Peak Allocated memory 4.4 MB
+      Peak Allocated memory 4.1 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
@@ -468,13 +462,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 14430 frames
+      Peak usage frame count: [0-1.0 KB]: 14512 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]: 14429 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 14511 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": 3.143310546875,
-            "min": 3.12618088722229,
-            "max": 3.1823134422302246,
+            "value": 3.0826170444488525,
+            "min": 3.0529732704162598,
+            "max": 3.1534907817840576,
             "count": 75
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 94148.4375,
-            "min": 22948.421875,
-            "max": 110132.390625,
+            "value": 88680.7265625,
+            "min": 17613.982421875,
+            "max": 100213.796875,
             "count": 75
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 752.0,
-            "min": 279.75,
-            "max": 999.0,
+            "value": 460.1666666666667,
+            "min": 216.95238095238096,
+            "max": 776.0,
             "count": 75
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 21056.0,
-            "min": 16032.0,
-            "max": 23644.0,
+            "value": 22088.0,
+            "min": 14780.0,
+            "max": 24932.0,
             "count": 75
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1243.9460686261082,
-            "min": 1225.3836834545552,
-            "max": 1244.904647863092,
-            "count": 74
+            "value": 1278.0626123633342,
+            "min": 1235.2334118823687,
+            "max": 1280.6322907660783,
+            "count": 75
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 12439.460686261082,
-            "min": 2479.1260412776337,
-            "max": 34536.608847381765,
-            "count": 74
+            "value": 25561.252247266686,
+            "min": 4989.136756322388,
+            "max": 51225.29163064313,
+            "count": 75
         },
         "SoccerTwos.Step.mean": {
-            "value": 2749838.0,
-            "min": 2009977.0,
-            "max": 2749838.0,
+            "value": 3499730.0,
+            "min": 2759046.0,
+            "max": 3499730.0,
             "count": 75
         },
         "SoccerTwos.Step.sum": {
-            "value": 2749838.0,
-            "min": 2009977.0,
-            "max": 2749838.0,
+            "value": 3499730.0,
+            "min": 2759046.0,
+            "max": 3499730.0,
             "count": 75
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.0013251889031380415,
-            "min": -0.013358287513256073,
-            "max": 0.021228041499853134,
+            "value": 0.0163666233420372,
+            "min": -0.008200411684811115,
+            "max": 0.04534551501274109,
             "count": 75
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -0.017227455973625183,
-            "min": -0.2538074553012848,
-            "max": 0.6580693125724792,
+            "value": 0.3927989602088928,
+            "min": -0.22961151599884033,
+            "max": 1.8138206005096436,
             "count": 75
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.0018061617156490684,
-            "min": -0.010150322690606117,
-            "max": 0.028209172189235687,
+            "value": 0.009769868105649948,
+            "min": -0.008772426284849644,
+            "max": 0.061527688056230545,
             "count": 75
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -0.02348010241985321,
-            "min": -0.2131567746400833,
-            "max": 0.8744843602180481,
+            "value": 0.23447683453559875,
+            "min": -0.18506309390068054,
+            "max": 2.1969051361083984,
             "count": 75
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
@@ -86,27 +86,27 @@
             "count": 75
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.10412307427479671,
-            "min": -0.7777777777777778,
-            "max": 0.4311058801763198,
+            "value": -0.24455000211795172,
+            "min": -0.5335870942761821,
+            "max": 0.44424000233411787,
             "count": 75
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -1.3535999655723572,
-            "min": -14.0,
-            "max": 10.378200024366379,
+            "value": -5.869200050830841,
+            "min": -16.541199922561646,
+            "max": 17.769600093364716,
             "count": 75
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.10412307427479671,
-            "min": -0.7777777777777778,
-            "max": 0.4311058801763198,
+            "value": -0.24455000211795172,
+            "min": -0.5335870942761821,
+            "max": 0.44424000233411787,
             "count": 75
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -1.3535999655723572,
-            "min": -14.0,
-            "max": 10.378200024366379,
+            "value": -5.869200050830841,
+            "min": -16.541199922561646,
+            "max": 17.769600093364716,
             "count": 75
         },
         "SoccerTwos.IsTraining.mean": {
@@ -122,51 +122,51 @@
             "count": 75
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.01642962825426366,
-            "min": 0.011811494338326156,
-            "max": 0.021366084227338433,
+            "value": 0.0163678941484856,
+            "min": 0.013363467935899582,
+            "max": 0.02322041514950494,
             "count": 35
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.01642962825426366,
-            "min": 0.011811494338326156,
-            "max": 0.021366084227338433,
+            "value": 0.0163678941484856,
+            "min": 0.013363467935899582,
+            "max": 0.02322041514950494,
             "count": 35
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.006246562682402631,
-            "min": 0.000759560749186979,
-            "max": 0.010220146272331476,
+            "value": 0.010916901628176372,
+            "min": 0.0049478520484020315,
+            "max": 0.014205682122459014,
             "count": 35
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.006246562682402631,
-            "min": 0.000759560749186979,
-            "max": 0.010220146272331476,
+            "value": 0.010916901628176372,
+            "min": 0.0049478520484020315,
+            "max": 0.014205682122459014,
             "count": 35
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.006464262865483761,
-            "min": 0.0007922046444339988,
-            "max": 0.010202337459971508,
+            "value": 0.011505619001885256,
+            "min": 0.005038972470598916,
+            "max": 0.014457402875026067,
             "count": 35
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.006464262865483761,
-            "min": 0.0007922046444339988,
-            "max": 0.010202337459971508,
+            "value": 0.011505619001885256,
+            "min": 0.005038972470598916,
+            "max": 0.014457402875026067,
             "count": 35
         },
         "SoccerTwos.Policy.LearningRate.mean": {
-            "value": 0.00045000000000000015,
-            "min": 0.00045000000000000015,
-            "max": 0.00045000000000000015,
+            "value": 0.0003999999999999999,
+            "min": 0.0003999999999999999,
+            "max": 0.0003999999999999999,
             "count": 35
         },
         "SoccerTwos.Policy.LearningRate.sum": {
-            "value": 0.00045000000000000015,
-            "min": 0.00045000000000000015,
-            "max": 0.00045000000000000015,
+            "value": 0.0003999999999999999,
+            "min": 0.0003999999999999999,
+            "max": 0.0003999999999999999,
             "count": 35
         },
         "SoccerTwos.Policy.Epsilon.mean": {
@@ -196,7 +196,7 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1690840321",
+        "start_time_seconds": "1690875386",
         "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": "1690843425"
+        "end_time_seconds": "1690878607"
     },
-    "total": 3103.470611474,
+    "total": 3221.02588012,
     "count": 1,
-    "self": 1.0652039069991588,
+    "self": 0.693373149999843,
     "children": {
         "run_training.setup": {
-            "total": 0.06217501600076503,
+            "total": 0.09810845300000892,
             "count": 1,
-            "self": 0.06217501600076503
+            "self": 0.09810845300000892
         },
         "TrainerController.start_learning": {
-            "total": 3102.3432325510003,
+            "total": 3220.234398517,
             "count": 1,
-            "self": 2.0396725200444052,
+            "self": 1.8983804490567309,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.1301726910005527,
+                    "total": 4.4790416780002715,
                     "count": 5,
-                    "self": 2.1301726910005527
+                    "self": 4.4790416780002715
                 },
                 "TrainerController.advance": {
-                    "total": 3097.826027655954,
-                    "count": 48718,
-                    "self": 1.9820340006608603,
+                    "total": 3213.611381196943,
+                    "count": 49107,
+                    "self": 2.13413384487194,
                     "children": {
                         "env_step": {
-                            "total": 1692.6302487570592,
-                            "count": 48718,
-                            "self": 1421.6117471499801,
+                            "total": 1764.9911412320362,
+                            "count": 49107,
+                            "self": 1481.702584109977,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 269.78835055523086,
-                                    "count": 48718,
-                                    "self": 12.689794163841725,
+                                    "total": 282.04487679306067,
+                                    "count": 49107,
+                                    "self": 13.714905159100056,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 257.09855639138914,
-                                            "count": 96196,
-                                            "self": 257.09855639138914
+                                            "total": 268.3299716339606,
+                                            "count": 96744,
+                                            "self": 268.3299716339606
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 1.2301510518482246,
-                                    "count": 48718,
+                                    "total": 1.2436803289986642,
+                                    "count": 49107,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 3086.3575241919243,
-                                            "count": 48718,
+                                            "total": 3200.7800029239825,
+                                            "count": 49107,
                                             "is_parallel": true,
-                                            "self": 1908.906176642644,
+                                            "self": 1974.9441368359787,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -265,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.005327139000655734,
+                                                            "total": 0.012773876999972344,
                                                             "count": 2,
                                                             "is_parallel": true,
-                                                            "self": 0.0011594800034799846,
+                                                            "self": 0.008126517999983207,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.004167658997175749,
+                                                                    "total": 0.004647358999989137,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.004167658997175749
+                                                                    "self": 0.004647358999989137
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.11118177200114587,
+                                                            "total": 0.061160170999983166,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0014464830037468346,
+                                                            "self": 0.0014477269999702003,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0009545169996272307,
+                                                                    "total": 0.0010304280000354993,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0009545169996272307
+                                                                    "self": 0.0010304280000354993
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.0883943979988544,
+                                                                    "total": 0.05436771599994472,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0883943979988544
+                                                                    "self": 0.05436771599994472
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.020386373998917406,
+                                                                    "total": 0.004314300000032745,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0008562319981137989,
+                                                                    "self": 0.000776908000034382,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.019530142000803608,
+                                                                            "total": 0.0035373919999983627,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.019530142000803608
+                                                                            "self": 0.0035373919999983627
                                                                         }
                                                                     }
                                                                 }
@@ -315,48 +315,48 @@
                                                     }
                                                 },
                                                 "steps_from_proto": {
-                                                    "total": 0.014887083001667634,
+                                                    "total": 0.014725805999944441,
                                                     "count": 8,
                                                     "is_parallel": true,
-                                                    "self": 0.002675308003745158,
+                                                    "self": 0.002693271000907771,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.012211774997922475,
+                                                            "total": 0.01203253499903667,
                                                             "count": 32,
                                                             "is_parallel": true,
-                                                            "self": 0.012211774997922475
+                                                            "self": 0.01203253499903667
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1177.4364604662787,
-                                                    "count": 48717,
+                                                    "total": 1225.8211402820039,
+                                                    "count": 49106,
                                                     "is_parallel": true,
-                                                    "self": 69.34796290724807,
+                                                    "self": 74.23583136709681,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 35.86445642198851,
-                                                            "count": 48717,
+                                                            "total": 39.960131956988164,
+                                                            "count": 49106,
                                                             "is_parallel": true,
-                                                            "self": 35.86445642198851
+                                                            "self": 39.960131956988164
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 852.5376701729547,
-                                                            "count": 48717,
+                                                            "total": 880.7466795869734,
+                                                            "count": 49106,
                                                             "is_parallel": true,
-                                                            "self": 852.5376701729547
+                                                            "self": 880.7466795869734
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 219.68637096408747,
-                                                            "count": 97434,
+                                                            "total": 230.87849737094558,
+                                                            "count": 98212,
                                                             "is_parallel": true,
-                                                            "self": 38.422194006059726,
+                                                            "self": 41.72440882700482,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 181.26417695802775,
-                                                                    "count": 389736,
+                                                                    "total": 189.15408854394076,
+                                                                    "count": 392848,
                                                                     "is_parallel": true,
-                                                                    "self": 181.26417695802775
+                                                                    "self": 189.15408854394076
                                                                 }
                                                             }
                                                         }
@@ -369,31 +369,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 1403.213744898234,
-                            "count": 48718,
-                            "self": 16.531713976008177,
+                            "total": 1446.486106120035,
+                            "count": 49107,
+                            "self": 15.844304215122065,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 189.87932542121962,
-                                    "count": 48718,
-                                    "self": 189.65393694721934,
+                                    "total": 198.5306375489116,
+                                    "count": 49107,
+                                    "self": 198.03153285191172,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.22538847400028317,
-                                            "count": 1,
-                                            "self": 0.22538847400028317
+                                            "total": 0.49910469699989335,
+                                            "count": 2,
+                                            "self": 0.49910469699989335
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 1196.8027055010061,
+                                    "total": 1232.1111643560014,
                                     "count": 35,
-                                    "self": 205.4372264820122,
+                                    "self": 207.44615126301028,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 991.3654790189939,
+                                            "total": 1024.665013092991,
                                             "count": 1050,
-                                            "self": 991.3654790189939
+                                            "self": 1024.665013092991
                                         }
                                     }
                                 }
@@ -402,19 +402,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.5559999155811965e-06,
+                    "total": 1.3130002116668038e-06,
                     "count": 1,
-                    "self": 1.5559999155811965e-06
+                    "self": 1.3130002116668038e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.34735812800136046,
+                    "total": 0.24559387999988758,
                     "count": 1,
-                    "self": 0.003031302001545555,
+                    "self": 0.002991471999848727,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.3443268259998149,
+                            "total": 0.24260240800003885,
                             "count": 1,
-                            "self": 0.3443268259998149
+                            "self": 0.24260240800003885
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,59 +2,59 @@
     "SoccerTwos": {
         "checkpoints": [
             {
-                "steps": 1500626,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-1500626.onnx",
+                "steps": 2499184,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-2499184.onnx",
                 "reward": 0.0,
-                "creation_time": 1690838130.059794,
+                "creation_time": 1690842357.9221148,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-1500626.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-2499184.pt"
                 ]
             },
             {
-                "steps": 1999130,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-1999130.onnx",
+                "steps": 2750550,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-2750550.onnx",
                 "reward": 0.0,
-                "creation_time": 1690840209.2941182,
+                "creation_time": 1690843424.1944873,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-1999130.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-2750550.pt"
                 ]
             },
             {
-                "steps": 2001130,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-2001130.onnx",
+                "steps": 2999941,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-2999941.onnx",
                 "reward": 0.0,
-                "creation_time": 1690840209.9085782,
+                "creation_time": 1690876440.796523,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-2001130.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-2999941.pt"
                 ]
             },
             {
-                "steps": 2499184,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-2499184.onnx",
+                "steps": 3499730,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3499730.onnx",
                 "reward": 0.0,
-                "creation_time": 1690842357.9221148,
+                "creation_time": 1690878606.362709,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-2499184.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-3499730.pt"
                 ]
             },
             {
-                "steps": 2750550,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-2750550.onnx",
+                "steps": 3501730,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3501730.onnx",
                 "reward": 0.0,
-                "creation_time": 1690843424.1944873,
+                "creation_time": 1690878606.9998047,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-2750550.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-3501730.pt"
                 ]
             }
         ],
-        "elo": 1243.9254633842545,
+        "elo": 1278.6843511527943,
         "final_checkpoint": {
-            "steps": 2750550,
+            "steps": 3501730,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1690843424.1944873,
+            "creation_time": 1690878606.9998047,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-2750550.pt"
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-3501730.pt"
             ]
         }
     },