Run id SoccerTwos1

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8ffc9f73b72ddf5834f567011f02f67adad03e89766cea30438fece3bb3e262
+oid sha256:05ef08c77b27274ab5884ba2f005ddc892012e0957a98c1941513238125da2f9
 size 1768747

SoccerTwos/SoccerTwos-1499969.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4b22d7890aa51216c9289fc9b1cfd771ef97c0385a5761da97babe69ce91fcb
+size 1768747

SoccerTwos/SoccerTwos-1499969.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4f2b96bfb4b3068223011b5dc34a87a280f43dce74126275a165970126510c1
+size 28432022

SoccerTwos/SoccerTwos-1999990.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ef08c77b27274ab5884ba2f005ddc892012e0957a98c1941513238125da2f9
+size 1768747

SoccerTwos/SoccerTwos-1999990.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fbf31c425c557c9f4e8a13b92e0eb3e088375c08ffee04717846d7deeb7cf09
+size 28432022

SoccerTwos/SoccerTwos-2000020.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ef08c77b27274ab5884ba2f005ddc892012e0957a98c1941513238125da2f9
+size 1768747

SoccerTwos/SoccerTwos-2000020.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df1d0fce6a4ef7e612f6fc6f4af4e697af8941e198961902fe5b5b754546e997
+size 28432022

SoccerTwos/SoccerTwos-499554.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed3b118e91397dd0f911b00db50e2eb945f1108fc69ae86b4d26b2af657f8f3f
+size 1768747

SoccerTwos/SoccerTwos-499554.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4be6d12e4fab03659384d6fa6ba49dabce52c190a8fe5fed913a79f6dede3cde
+size 28431898

SoccerTwos/SoccerTwos-999909.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9dc94549effec3f5ed47f9283fc0b494adda1d94249d63cf98b8e58e0d6e5f9
+size 1768747

SoccerTwos/SoccerTwos-999909.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:349570880e67d7f231a1103836a3049c79393d0c733e683d2387c789fe7d8270
+size 28431898

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18031c71955ef7482fe9bc55345a370e3a874e772b48547a0d72f1753e506d0f
+oid sha256:8c1a0a554fe03faa71583941f1c7dc68dee6833f34be81a20d7196ca3496c18b
 size 28431030

SoccerTwos/events.out.tfevents.1724401380.W11-AI24.57124.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:676352d709a6a49e412be1fe27e7baf6ae65f29dcf46f8c317e41e3117d34265
+size 2009804

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": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 500000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 20000, "team_change": 150000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "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, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"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": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 2000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 20000, "team_change": 150000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "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, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -37,7 +37,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 500000
+    max_steps: 2000000
     time_horizon: 1000
     summary_freq: 10000
     threaded: false
@@ -71,7 +71,7 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: SoccerTwos
+  run_id: SoccerTwos1
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -2,8 +2,6 @@ Mono path[0] = '/home/ai24/condaprojects/hfrl/hfrl7/ml-agents/training-envs-exec
 Mono config path = '/home/ai24/condaprojects/hfrl/hfrl7/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/MonoBleedingEdge/etc'
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /home/ai24/.config/unity3d/Unity Technologies/SoccerTwos
-Unable to load player prefs
 Initialize engine version: 2021.3.14f1 (eee1884e7226)
 [Subsystems] Discovering subsystems at path /home/ai24/condaprojects/hfrl/hfrl7/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -13,7 +11,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.032 seconds
+- Completed reload, in  0.050 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)
@@ -38,7 +36,7 @@ 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: 0.358412 ms
+UnloadTime: 0.336744 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
@@ -177,106 +175,12 @@ TOO LONG
 TOO LONG
 TOO LONG
 TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
 Setting up 16 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]: 9985 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 38088 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
@@ -416,12 +320,12 @@ Memory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 26]
+    [ALLOC_TEMP_Job.Worker 21]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 21]
+    [ALLOC_TEMP_Job.Worker 26]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
@@ -499,7 +403,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 7]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 0.7 KB
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 23]
       Initial Block Size 256.0 KB
@@ -516,25 +420,25 @@ Memory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 15]
+    [ALLOC_TEMP_Job.Worker 24]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 24]
+    [ALLOC_TEMP_Job.Worker 15]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 12]
+    [ALLOC_TEMP_Job.Worker 19]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 19]
+    [ALLOC_TEMP_Job.Worker 12]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0.7 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Loading.AsyncRead]
       Initial Block Size 64.0 KB
@@ -542,22 +446,22 @@ Memory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 3
+  Peak main deferred allocation count 6
     [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]: 9986 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 38089 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 4.8 MB
+      Peak Allocated memory 4.7 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 9986 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 38089 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.4 MB
+      Peak Allocated memory 17.5 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -586,13 +490,13 @@ 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]: 9985 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 38088 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]: 9986 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 38089 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.5 KB
@@ -604,13 +508,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 9986 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 38089 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]: 9985 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 38088 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.5 MB
@@ -622,13 +526,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 9986 frames
+      Peak usage frame count: [0-1.0 KB]: 38089 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]: 9985 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 38088 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

@@ -2,261 +2,261 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 3.206151247024536,
-            "min": 3.196983575820923,
-            "max": 3.2957115173339844,
-            "count": 50
+            "value": 2.307533025741577,
+            "min": 2.307533025741577,
+            "max": 3.295701742172241,
+            "count": 200
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 80435.921875,
-            "min": 30138.3515625,
-            "max": 118419.390625,
-            "count": 50
+            "value": 45781.45703125,
+            "min": 16348.001953125,
+            "max": 107780.3984375,
+            "count": 200
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 856.3333333333334,
-            "min": 402.5833333333333,
+            "value": 57.55555555555556,
+            "min": 47.41747572815534,
             "max": 999.0,
-            "count": 50
+            "count": 200
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 20552.0,
-            "min": 15028.0,
-            "max": 24916.0,
-            "count": 50
+            "value": 18648.0,
+            "min": 16692.0,
+            "max": 23948.0,
+            "count": 200
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1207.074629580175,
-            "min": 1200.3774895761717,
-            "max": 1207.074629580175,
-            "count": 35
+            "value": 1450.8970232833933,
+            "min": 1198.931713842262,
+            "max": 1462.3359987395977,
+            "count": 198
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 4828.2985183207,
-            "min": 2405.69935100464,
-            "max": 12047.01731677414,
-            "count": 35
+            "value": 235045.31777190973,
+            "min": 2404.477419571058,
+            "max": 286527.4587735868,
+            "count": 198
         },
         "SoccerTwos.Step.mean": {
-            "value": 499292.0,
-            "min": 9730.0,
-            "max": 499292.0,
-            "count": 50
+            "value": 1999990.0,
+            "min": 9998.0,
+            "max": 1999990.0,
+            "count": 200
         },
         "SoccerTwos.Step.sum": {
-            "value": 499292.0,
-            "min": 9730.0,
-            "max": 499292.0,
-            "count": 50
+            "value": 1999990.0,
+            "min": 9998.0,
+            "max": 1999990.0,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": 0.001526641775853932,
-            "min": -0.02495989017188549,
-            "max": 0.003064664313569665,
-            "count": 50
+            "value": -0.03722770884633064,
+            "min": -0.07136625796556473,
+            "max": 0.18781158328056335,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": 0.01831970177590847,
-            "min": -0.2995186746120453,
-            "max": 0.06091596186161041,
-            "count": 50
+            "value": -6.030888557434082,
+            "min": -11.632699966430664,
+            "max": 19.53240394592285,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.0019540293142199516,
-            "min": -0.02800181321799755,
-            "max": 0.0030761943198740482,
-            "count": 50
+            "value": -0.035194698721170425,
+            "min": -0.07054449617862701,
+            "max": 0.17647695541381836,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 0.02344835177063942,
-            "min": -0.33602175116539,
-            "max": 0.05378138646483421,
-            "count": 50
+            "value": -5.701540946960449,
+            "min": -11.49875259399414,
+            "max": 18.35360336303711,
+            "count": 200
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 50
+            "count": 200
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 50
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": 0.14263333876927695,
-            "min": -0.625,
-            "max": 0.19090000291665396,
-            "count": 50
+            "value": -0.16177530862666942,
+            "min": -0.5347517194419071,
+            "max": 0.5304096129078132,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": 1.7116000652313232,
-            "min": -10.0,
-            "max": 2.2908000349998474,
-            "count": 50
+            "value": -26.207599997520447,
+            "min": -44.9700003862381,
+            "max": 55.16259974241257,
+            "count": 200
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": 0.14263333876927695,
-            "min": -0.625,
-            "max": 0.19090000291665396,
-            "count": 50
+            "value": -0.16177530862666942,
+            "min": -0.5347517194419071,
+            "max": 0.5304096129078132,
+            "count": 200
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": 1.7116000652313232,
-            "min": -10.0,
-            "max": 2.2908000349998474,
-            "count": 50
+            "value": -26.207599997520447,
+            "min": -44.9700003862381,
+            "max": 55.16259974241257,
+            "count": 200
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 50
+            "count": 200
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 50
+            "count": 200
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.014959967434212256,
-            "min": 0.011192784489442905,
-            "max": 0.024584695386389892,
-            "count": 23
+            "value": 0.018693920023118458,
+            "min": 0.012543374454253353,
+            "max": 0.02186436578388869,
+            "count": 96
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.014959967434212256,
-            "min": 0.011192784489442905,
-            "max": 0.024584695386389892,
-            "count": 23
+            "value": 0.018693920023118458,
+            "min": 0.012543374454253353,
+            "max": 0.02186436578388869,
+            "count": 96
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 7.660284512288248e-05,
-            "min": 1.196910857288458e-05,
-            "max": 0.004040644955680225,
-            "count": 23
+            "value": 0.1002560280263424,
+            "min": 0.0022964858333580198,
+            "max": 0.10743579690655072,
+            "count": 96
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 7.660284512288248e-05,
-            "min": 1.196910857288458e-05,
-            "max": 0.004040644955680225,
-            "count": 23
+            "value": 0.1002560280263424,
+            "min": 0.0022964858333580198,
+            "max": 0.10743579690655072,
+            "count": 96
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 7.809184874834803e-05,
-            "min": 1.2936575437076196e-05,
-            "max": 0.0039288965752348306,
-            "count": 23
+            "value": 0.1014141634106636,
+            "min": 0.002313785251074781,
+            "max": 0.10904582043488821,
+            "count": 96
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 7.809184874834803e-05,
-            "min": 1.2936575437076196e-05,
-            "max": 0.0039288965752348306,
-            "count": 23
+            "value": 0.1014141634106636,
+            "min": 0.002313785251074781,
+            "max": 0.10904582043488821,
+            "count": 96
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 23
+            "count": 96
         },
         "SoccerTwos.Policy.LearningRate.sum": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 23
+            "count": 96
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.20000000000000007,
-            "min": 0.2,
+            "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 23
+            "count": 96
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.20000000000000007,
-            "min": 0.2,
+            "min": 0.20000000000000007,
             "max": 0.20000000000000007,
-            "count": 23
+            "count": 96
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.005000000000000001,
-            "min": 0.005,
+            "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 23
+            "count": 96
         },
         "SoccerTwos.Policy.Beta.sum": {
             "value": 0.005000000000000001,
-            "min": 0.005,
+            "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 23
+            "count": 96
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1724399974",
+        "start_time_seconds": "1724401380",
         "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
-        "command_line_arguments": "/home/ai24/miniconda3/envs/hfrl7/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics",
+        "command_line_arguments": "/home/ai24/miniconda3/envs/hfrl7/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos1 --no-graphics",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.4.0+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1724400545"
+        "end_time_seconds": "1724403708"
     },
-    "total": 570.7435585329986,
+    "total": 2327.9935854979994,
     "count": 1,
-    "self": 0.1668835409982421,
+    "self": 0.16762781600118615,
     "children": {
         "run_training.setup": {
-            "total": 0.009389012999236002,
+            "total": 0.010233298999082763,
             "count": 1,
-            "self": 0.009389012999236002
+            "self": 0.010233298999082763
         },
         "TrainerController.start_learning": {
-            "total": 570.5672859790011,
+            "total": 2327.815724382999,
             "count": 1,
-            "self": 0.3545561500468466,
+            "self": 1.452581569461472,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 1.1179535159990337,
-                    "count": 4,
-                    "self": 1.1179535159990337
+                    "total": 1.234213148998606,
+                    "count": 14,
+                    "self": 1.234213148998606
                 },
                 "TrainerController.advance": {
-                    "total": 568.992186374955,
-                    "count": 33520,
-                    "self": 0.3552299881539511,
+                    "total": 2325.0313145595373,
+                    "count": 135732,
+                    "self": 1.3759033780588652,
                     "children": {
                         "env_step": {
-                            "total": 494.43640590888026,
-                            "count": 33520,
-                            "self": 307.941048131559,
+                            "total": 1898.9211854298665,
+                            "count": 135732,
+                            "self": 1191.3522834903215,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 186.24845910115982,
-                                    "count": 33520,
-                                    "self": 2.677762361459827,
+                                    "total": 706.6355211982664,
+                                    "count": 135732,
+                                    "self": 9.782920157484114,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 183.5706967397,
-                                            "count": 66574,
-                                            "self": 183.5706967397
+                                            "total": 696.8526010407822,
+                                            "count": 253936,
+                                            "self": 696.8526010407822
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.24689867616143601,
-                                    "count": 33520,
+                                    "total": 0.9333807412785973,
+                                    "count": 135732,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 569.5112755150403,
-                                            "count": 33520,
+                                            "total": 2324.5866881452966,
+                                            "count": 135732,
                                             "is_parallel": true,
-                                            "self": 302.8778859350168,
+                                            "self": 1284.9388557016919,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -265,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0016181609989871504,
+                                                            "total": 0.0015676800012442982,
                                                             "count": 2,
                                                             "is_parallel": true,
-                                                            "self": 0.0006444920018111588,
+                                                            "self": 0.0006105560005380539,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0009736689971759915,
+                                                                    "total": 0.0009571240007062443,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0009736689971759915
+                                                                    "self": 0.0009571240007062443
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.01531866400000581,
+                                                            "total": 0.014677770999696804,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00026243299907946493,
+                                                            "self": 0.0002704719972825842,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00019157299902872182,
+                                                                    "total": 0.0001934970005095238,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00019157299902872182
+                                                                    "self": 0.0001934970005095238
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.014141837000352098,
+                                                                    "total": 0.013495855000655865,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.014141837000352098
+                                                                    "self": 0.013495855000655865
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0007228210015455261,
+                                                                    "total": 0.0007179470012488309,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00015099000302143395,
+                                                                    "self": 0.00014968599862186238,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0005718309985240921,
+                                                                            "total": 0.0005682610026269685,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0005718309985240921
+                                                                            "self": 0.0005682610026269685
                                                                         }
                                                                     }
                                                                 }
@@ -315,50 +315,50 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 266.63109096702465,
-                                                    "count": 33519,
+                                                    "total": 1039.6382544476055,
+                                                    "count": 135731,
                                                     "is_parallel": true,
-                                                    "self": 8.28771804608914,
+                                                    "self": 32.022296717377685,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 5.201358522261216,
-                                                            "count": 33519,
+                                                            "total": 19.758511124269717,
+                                                            "count": 135731,
                                                             "is_parallel": true,
-                                                            "self": 5.201358522261216
+                                                            "self": 19.758511124269717
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 230.52292082589884,
-                                                            "count": 33519,
+                                                            "total": 901.0258305711704,
+                                                            "count": 135731,
                                                             "is_parallel": true,
-                                                            "self": 230.52292082589884
+                                                            "self": 901.0258305711704
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 22.619093572775455,
-                                                            "count": 67038,
+                                                            "total": 86.83161603478766,
+                                                            "count": 271462,
                                                             "is_parallel": true,
-                                                            "self": 4.5722352008288,
+                                                            "self": 17.1833065849587,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 18.046858371946655,
-                                                                    "count": 268152,
+                                                                    "total": 69.64830944982896,
+                                                                    "count": 1085848,
                                                                     "is_parallel": true,
-                                                                    "self": 18.046858371946655
+                                                                    "self": 69.64830944982896
                                                                 }
                                                             }
                                                         }
                                                     }
                                                 },
                                                 "steps_from_proto": {
-                                                    "total": 0.0022986129988566972,
-                                                    "count": 6,
+                                                    "total": 0.009577995999279665,
+                                                    "count": 26,
                                                     "is_parallel": true,
-                                                    "self": 0.00048140900253201835,
+                                                    "self": 0.001984607002668781,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.0018172039963246789,
-                                                            "count": 24,
+                                                            "total": 0.007593388996610884,
+                                                            "count": 104,
                                                             "is_parallel": true,
-                                                            "self": 0.0018172039963246789
+                                                            "self": 0.007593388996610884
                                                         }
                                                     }
                                                 }
@@ -369,31 +369,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 74.20055047792084,
-                            "count": 33520,
-                            "self": 3.168746309922426,
+                            "total": 424.73422575161203,
+                            "count": 135732,
+                            "self": 11.67938789940672,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 23.117011589996764,
-                                    "count": 33520,
-                                    "self": 22.994344105996788,
+                                    "total": 220.90293864320665,
+                                    "count": 135732,
+                                    "self": 220.38989543920616,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.12266748399997596,
-                                            "count": 1,
-                                            "self": 0.12266748399997596
+                                            "total": 0.5130432040004962,
+                                            "count": 4,
+                                            "self": 0.5130432040004962
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 47.91479257800165,
-                                    "count": 23,
-                                    "self": 25.600113978032823,
+                                    "total": 192.15189920899866,
+                                    "count": 96,
+                                    "self": 100.72317268801817,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 22.31467859996883,
-                                            "count": 693,
-                                            "self": 22.31467859996883
+                                            "total": 91.42872652098049,
+                                            "count": 2880,
+                                            "self": 91.42872652098049
                                         }
                                     }
                                 }
@@ -402,19 +402,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 5.149995558895171e-07,
+                    "total": 5.070014594821259e-07,
                     "count": 1,
-                    "self": 5.149995558895171e-07
+                    "self": 5.070014594821259e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.1025894230006088,
+                    "total": 0.09761459800029115,
                     "count": 1,
-                    "self": 0.0005897810005990323,
+                    "self": 0.0006807940008002333,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.10199964200000977,
+                            "total": 0.09693380399949092,
                             "count": 1,
-                            "self": 0.10199964200000977
+                            "self": 0.09693380399949092
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,32 +2,59 @@
     "SoccerTwos": {
         "checkpoints": [
             {
-                "steps": 499292,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-499292.onnx",
+                "steps": 499554,
+                "file_path": "results/SoccerTwos1/SoccerTwos/SoccerTwos-499554.onnx",
                 "reward": 0.0,
-                "creation_time": 1724400545.3596063,
+                "creation_time": 1724401941.4187784,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-499292.pt"
+                    "results/SoccerTwos1/SoccerTwos/SoccerTwos-499554.pt"
                 ]
             },
             {
-                "steps": 501292,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-501292.onnx",
+                "steps": 999909,
+                "file_path": "results/SoccerTwos1/SoccerTwos/SoccerTwos-999909.onnx",
                 "reward": 0.0,
-                "creation_time": 1724400545.5519145,
+                "creation_time": 1724402520.440714,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-501292.pt"
+                    "results/SoccerTwos1/SoccerTwos/SoccerTwos-999909.pt"
+                ]
+            },
+            {
+                "steps": 1499969,
+                "file_path": "results/SoccerTwos1/SoccerTwos/SoccerTwos-1499969.onnx",
+                "reward": 0.0,
+                "creation_time": 1724403117.087102,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos1/SoccerTwos/SoccerTwos-1499969.pt"
+                ]
+            },
+            {
+                "steps": 1999990,
+                "file_path": "results/SoccerTwos1/SoccerTwos/SoccerTwos-1999990.onnx",
+                "reward": 0.0,
+                "creation_time": 1724403708.2979827,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos1/SoccerTwos/SoccerTwos-1999990.pt"
+                ]
+            },
+            {
+                "steps": 2000020,
+                "file_path": "results/SoccerTwos1/SoccerTwos/SoccerTwos-2000020.onnx",
+                "reward": 0.0,
+                "creation_time": 1724403708.4089499,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos1/SoccerTwos/SoccerTwos-2000020.pt"
                 ]
             }
         ],
-        "elo": 1207.819604153656,
+        "elo": 1448.39106905449,
         "final_checkpoint": {
-            "steps": 501292,
-            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "steps": 2000020,
+            "file_path": "results/SoccerTwos1/SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1724400545.5519145,
+            "creation_time": 1724403708.4089499,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-501292.pt"
+                "results/SoccerTwos1/SoccerTwos/SoccerTwos-2000020.pt"
             ]
         }
     },