First Push`

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55071c72c18aed94856b73b23bd9c2af43311581c61390ba946dfc0b67134bb1
+oid sha256:e4238a2b837774243b599200ad3c462c84eac3804db6934edb3a8b728148d20d
 size 1764626

SoccerTwos/{SoccerTwos-101618.onnx → SoccerTwos-1499832.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55071c72c18aed94856b73b23bd9c2af43311581c61390ba946dfc0b67134bb1
+oid sha256:879de74f54747e4d53e9a6600e802a806c49cfdddd12be4167fbe8d63c64525c
 size 1764626

SoccerTwos/{SoccerTwos-101618.pt → SoccerTwos-1499832.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60b2691e00d69d7d20f4a4f702c7a4e66ee8d4ffa8b6960634d0156c6eb5c328
+oid sha256:5bd82091ff315c28b0e69f0cb75534e9a9eee03e1bc78864efbac742614ea12c
 size 28428241

SoccerTwos/{events.out.tfevents.1678303734.DESKTOP-3SFF1V4.13132.0 → SoccerTwos-1999990.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d5eec391dc40add00d627ff30d7ccf90e9f8ddd77af70b634323f79c6ba4764
-size 65840
+oid sha256:e4238a2b837774243b599200ad3c462c84eac3804db6934edb3a8b728148d20d
+size 1764626

SoccerTwos/SoccerTwos-1999990.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2922b5aad480d55922e19e7eb1e7b545921610ccc2c412045de1e2d039edb90
+size 28428241

SoccerTwos/SoccerTwos-2000062.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4238a2b837774243b599200ad3c462c84eac3804db6934edb3a8b728148d20d
+size 1764626

SoccerTwos/SoccerTwos-2000062.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:817b3671fc16658d443350b6a95cb15201f724217db366a161f82f89be55bb83
+size 28428241

SoccerTwos/SoccerTwos-499248.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ce2eb7d1c0ed471b4b5bd356787fd500cdee8aef4524c327815f8cf368c8c73
+size 1764626

SoccerTwos/SoccerTwos-499248.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f6d30d50e60e781ef0a137b9111fa621b1cd7f1199de6489837dadb9bfe5453
+size 28428241

SoccerTwos/SoccerTwos-999955.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20cce5d5b72f1061af983329d4f6e5ec02ceb7c0ee4d7450083009490571e444
+size 1764626

SoccerTwos/SoccerTwos-999955.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a76b0bf81e9a5e046939a7df0e1ed9baebfedb17a3722f57c0fc4623dc2dc90a
+size 28428241

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60b2691e00d69d7d20f4a4f702c7a4e66ee8d4ffa8b6960634d0156c6eb5c328
+oid sha256:817b3671fc16658d443350b6a95cb15201f724217db366a161f82f89be55bb83
 size 28428241

SoccerTwos/events.out.tfevents.1678304695.DESKTOP-3SFF1V4.12204.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33993e2d81fbf7837995215cf6ee1c86e76abaa4c35499c59af61037e4aabd93
+size 1915148

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": 100000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "C:\\rl\\ml-agents\\training-envs-executables\\SoccerTwos\\SoccerTwos.exe", "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": "SoccerTwos100kc", "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": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "C:\\rl\\ml-agents\\training-envs-executables\\SoccerTwos\\SoccerTwos.exe", "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": "SoccerTwos2Ma", "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: 100000
+    max_steps: 2000000
     time_horizon: 1000
     summary_freq: 10000
     threaded: false
@@ -69,7 +69,7 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: SoccerTwos100kc
+  run_id: SoccerTwos2Ma
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -9,7 +9,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.100 seconds
+- Completed reload, in  0.101 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 Microsoft Media Foundation video decoding to texture disabled: graphics device is Null, only Direct3D 11 and Direct3D 12 (only on desktop) are supported for hardware-accelerated video decoding.
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -35,7 +35,7 @@ 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: 0.717700 ms
+UnloadTime: 0.769700 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 TOO LONG
@@ -81,12 +81,234 @@ 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
+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
+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 6 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]: 2043 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 38063 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -144,7 +366,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 4]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0.8 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 3]
       Initial Block Size 256.0 KB
@@ -234,7 +456,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 10]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 54 B
+      Peak Allocated Bytes 0.8 KB
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 0]
       Initial Block Size 32.0 KB
@@ -252,22 +474,22 @@ Memory Statistics:
       Peak Allocated Bytes 54 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 2
+  Peak main deferred allocation count 7
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 2044 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 38064 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.1 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]: 2044 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 38064 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.3 MB
+      Peak Allocated memory 17.4 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -296,13 +518,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 2043 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 38063 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]: 2044 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 38064 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.6 KB
@@ -314,13 +536,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 2044 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 38064 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]: 2043 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 38063 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 MB
@@ -332,13 +554,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 2044 frames
+      Peak usage frame count: [0-1.0 KB]: 38064 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]: 2043 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 38063 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

@@ -2,305 +2,305 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 3.274366617202759,
-            "min": 3.273391008377075,
-            "max": 3.2957680225372314,
-            "count": 10
+            "value": 2.3724489212036133,
+            "min": 2.35398006439209,
+            "max": 3.295729160308838,
+            "count": 200
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 85185.921875,
-            "min": 36176.7109375,
-            "max": 105464.578125,
-            "count": 10
+            "value": 46613.875,
+            "min": 11777.2392578125,
+            "max": 105463.28125,
+            "count": 200
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 803.1428571428571,
-            "min": 572.2,
+            "value": 60.13414634146341,
+            "min": 47.601941747572816,
             "max": 999.0,
-            "count": 10
+            "count": 200
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 22488.0,
-            "min": 11444.0,
-            "max": 28852.0,
-            "count": 10
+            "value": 19724.0,
+            "min": 11628.0,
+            "max": 30448.0,
+            "count": 200
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1199.7897401019268,
-            "min": 1198.0313712553805,
-            "max": 1200.6346709108686,
-            "count": 7
+            "value": 1498.0635172021985,
+            "min": 1200.7142360791336,
+            "max": 1498.4165916460247,
+            "count": 192
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 4799.158960407707,
-            "min": 2398.5014391117093,
-            "max": 9594.040092560455,
-            "count": 7
+            "value": 245682.41682116053,
+            "min": 2403.259069081372,
+            "max": 301467.75996944495,
+            "count": 192
         },
         "SoccerTwos.Step.mean": {
-            "value": 99618.0,
-            "min": 9442.0,
-            "max": 99618.0,
-            "count": 10
+            "value": 1999990.0,
+            "min": 9242.0,
+            "max": 1999990.0,
+            "count": 200
         },
         "SoccerTwos.Step.sum": {
-            "value": 99618.0,
-            "min": 9442.0,
-            "max": 99618.0,
-            "count": 10
+            "value": 1999990.0,
+            "min": 9242.0,
+            "max": 1999990.0,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.020365266129374504,
-            "min": -0.04041188582777977,
-            "max": -0.020003842189908028,
-            "count": 10
+            "value": -0.03040555864572525,
+            "min": -0.04107595607638359,
+            "max": 0.1871304214000702,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -0.2647484540939331,
-            "min": -0.56570965051651,
-            "max": -0.20003841817378998,
-            "count": 10
+            "value": -4.956106185913086,
+            "min": -7.475823879241943,
+            "max": 28.900962829589844,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.020473986864089966,
-            "min": -0.0403805635869503,
-            "max": -0.020473986864089966,
-            "count": 10
+            "value": -0.025555307045578957,
+            "min": -0.03806399181485176,
+            "max": 0.19258709251880646,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -0.26616182923316956,
-            "min": -0.5653278827667236,
-            "max": -0.20855936408042908,
-            "count": 10
+            "value": -4.165514945983887,
+            "min": -6.927646636962891,
+            "max": 28.431549072265625,
+            "count": 200
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 10
+            "count": 200
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 10
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.3076923076923077,
-            "min": -0.3076923076923077,
-            "max": 0.11043636365370317,
-            "count": 10
+            "value": -0.07679509019559147,
+            "min": -0.7142857142857143,
+            "max": 0.498006720001958,
+            "count": 200
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -4.0,
-            "min": -4.0,
-            "max": 1.2148000001907349,
-            "count": 10
+            "value": -12.517599701881409,
+            "min": -36.26460003852844,
+            "max": 63.30120038986206,
+            "count": 200
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.3076923076923077,
-            "min": -0.3076923076923077,
-            "max": 0.11043636365370317,
-            "count": 10
+            "value": -0.07679509019559147,
+            "min": -0.7142857142857143,
+            "max": 0.498006720001958,
+            "count": 200
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -4.0,
-            "min": -4.0,
-            "max": 1.2148000001907349,
-            "count": 10
+            "value": -12.517599701881409,
+            "min": -36.26460003852844,
+            "max": 63.30120038986206,
+            "count": 200
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 10
+            "count": 200
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 10
+            "count": 200
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.015362099460617173,
-            "min": 0.015362099460617173,
-            "max": 0.019046683927687505,
-            "count": 4
+            "value": 0.01417751678188021,
+            "min": 0.012125546843162738,
+            "max": 0.023403239927332228,
+            "count": 95
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.015362099460617173,
-            "min": 0.015362099460617173,
-            "max": 0.019046683927687505,
-            "count": 4
+            "value": 0.01417751678188021,
+            "min": 0.012125546843162738,
+            "max": 0.023403239927332228,
+            "count": 95
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.0008241575856421453,
-            "min": 0.0008241575856421453,
-            "max": 0.00300423198301966,
-            "count": 4
+            "value": 0.10028252626458804,
+            "min": 0.0003658233804647656,
+            "max": 0.10883518730600675,
+            "count": 95
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.0008241575856421453,
-            "min": 0.0008241575856421453,
-            "max": 0.00300423198301966,
-            "count": 4
+            "value": 0.10028252626458804,
+            "min": 0.0003658233804647656,
+            "max": 0.10883518730600675,
+            "count": 95
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.000829946580536974,
-            "min": 0.000829946580536974,
-            "max": 0.003044945471143971,
-            "count": 4
+            "value": 0.10191588525970777,
+            "min": 0.0003673039436156008,
+            "max": 0.11179724062482516,
+            "count": 95
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.000829946580536974,
-            "min": 0.000829946580536974,
-            "max": 0.003044945471143971,
-            "count": 4
+            "value": 0.10191588525970777,
+            "min": 0.0003673039436156008,
+            "max": 0.11179724062482516,
+            "count": 95
         },
         "SoccerTwos.Policy.LearningRate.mean": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 4
+            "count": 95
         },
         "SoccerTwos.Policy.LearningRate.sum": {
             "value": 0.0003,
             "min": 0.0003,
             "max": 0.0003,
-            "count": 4
+            "count": 95
         },
         "SoccerTwos.Policy.Epsilon.mean": {
             "value": 0.20000000000000007,
             "min": 0.20000000000000004,
             "max": 0.20000000000000007,
-            "count": 4
+            "count": 95
         },
         "SoccerTwos.Policy.Epsilon.sum": {
             "value": 0.20000000000000007,
             "min": 0.20000000000000004,
             "max": 0.20000000000000007,
-            "count": 4
+            "count": 95
         },
         "SoccerTwos.Policy.Beta.mean": {
             "value": 0.005000000000000001,
             "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 4
+            "count": 95
         },
         "SoccerTwos.Policy.Beta.sum": {
             "value": 0.005000000000000001,
             "min": 0.005000000000000001,
             "max": 0.005000000000000001,
-            "count": 4
+            "count": 95
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1678303731",
+        "start_time_seconds": "1678304692",
         "python_version": "3.9.16 (main, Mar  8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]",
-        "command_line_arguments": "C:\\Users\\jacky\\.conda\\envs\\rl\\Scripts\\mlagents-learn C:\\rl\\ml-agents\\config\\poca\\SoccerTwos.yaml --env=C:\\rl\\ml-agents\\training-envs-executables\\SoccerTwos\\SoccerTwos.exe --run-id=SoccerTwos100kc --no-graphics",
+        "command_line_arguments": "C:\\Users\\jacky\\.conda\\envs\\rl\\Scripts\\mlagents-learn C:\\rl\\ml-agents\\config\\poca\\SoccerTwos.yaml --env=C:\\rl\\ml-agents\\training-envs-executables\\SoccerTwos\\SoccerTwos.exe --run-id=SoccerTwos2Ma --no-graphics",
         "mlagents_version": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.12.1+cpu",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1678304076"
+        "end_time_seconds": "1678311717"
     },
-    "total": 344.6660497,
+    "total": 7024.9085793,
     "count": 1,
-    "self": 0.3372092999999836,
+    "self": 0.3392129000003479,
     "children": {
         "run_training.setup": {
-            "total": 0.10126900000000005,
+            "total": 0.11652259999999992,
             "count": 1,
-            "self": 0.10126900000000005
+            "self": 0.11652259999999992
         },
         "TrainerController.start_learning": {
-            "total": 344.2275714,
+            "total": 7024.4528438,
             "count": 1,
-            "self": 0.21356549999944718,
+            "self": 4.133327600093253,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.3736867000000004,
-                    "count": 1,
-                    "self": 3.3736867000000004
+                    "total": 3.228551299999737,
+                    "count": 10,
+                    "self": 3.228551299999737
                 },
                 "TrainerController.advance": {
-                    "total": 340.1922546000006,
-                    "count": 6849,
-                    "self": 0.23115789999809522,
+                    "total": 7016.774306299907,
+                    "count": 133823,
+                    "self": 4.316766599808034,
                     "children": {
                         "env_step": {
-                            "total": 182.51540820000014,
-                            "count": 6849,
-                            "self": 143.5209157999982,
+                            "total": 3422.673846700017,
+                            "count": 133823,
+                            "self": 2706.226638800106,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 38.849259800002216,
-                                    "count": 6849,
-                                    "self": 1.3681651999992042,
+                                    "total": 713.6143469999643,
+                                    "count": 133823,
+                                    "self": 23.942558899763412,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 37.48109460000301,
-                                            "count": 13626,
-                                            "self": 37.48109460000301
+                                            "total": 689.6717881002008,
+                                            "count": 253760,
+                                            "self": 689.6717881002008
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.14523259999971216,
-                                    "count": 6849,
+                                    "total": 2.832860899946846,
+                                    "count": 133823,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 339.63461360000196,
-                                            "count": 6849,
+                                            "total": 7015.33651089996,
+                                            "count": 133823,
                                             "is_parallel": true,
-                                            "self": 223.1723554000015,
+                                            "self": 4809.827519199924,
                                             "children": {
                                                 "steps_from_proto": {
-                                                    "total": 0.0019049999999998235,
-                                                    "count": 2,
+                                                    "total": 0.022868199999835248,
+                                                    "count": 20,
                                                     "is_parallel": true,
-                                                    "self": 0.00040420000000018774,
+                                                    "self": 0.004605199995329823,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.0015007999999996358,
-                                                            "count": 8,
+                                                            "total": 0.018263000004505425,
+                                                            "count": 80,
                                                             "is_parallel": true,
-                                                            "self": 0.0015007999999996358
+                                                            "self": 0.018263000004505425
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 116.46035320000045,
-                                                    "count": 6849,
+                                                    "total": 2205.4861235000367,
+                                                    "count": 133823,
                                                     "is_parallel": true,
-                                                    "self": 5.689601299998628,
+                                                    "self": 107.46140500010642,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 4.511647499999814,
-                                                            "count": 6849,
+                                                            "total": 82.49900079976463,
+                                                            "count": 133823,
                                                             "is_parallel": true,
-                                                            "self": 4.511647499999814
+                                                            "self": 82.49900079976463
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 88.35620720000017,
-                                                            "count": 6849,
+                                                            "total": 1685.0467167998993,
+                                                            "count": 133823,
                                                             "is_parallel": true,
-                                                            "self": 88.35620720000017
+                                                            "self": 1685.0467167998993
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 17.90289720000185,
-                                                            "count": 13698,
+                                                            "total": 330.47900090026644,
+                                                            "count": 267646,
                                                             "is_parallel": true,
-                                                            "self": 3.6238450000039464,
+                                                            "self": 67.6377834999011,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 14.279052199997903,
-                                                                    "count": 54792,
+                                                                    "total": 262.84121740036534,
+                                                                    "count": 1070584,
                                                                     "is_parallel": true,
-                                                                    "self": 14.279052199997903
+                                                                    "self": 262.84121740036534
                                                                 }
                                                             }
                                                         }
@@ -313,24 +313,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 157.44568850000232,
-                            "count": 6849,
-                            "self": 1.217458900001958,
+                            "total": 3589.7836930000817,
+                            "count": 133823,
+                            "self": 28.07474030005551,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 24.482369700000326,
-                                    "count": 6849,
-                                    "self": 24.482369700000326
+                                    "total": 593.3459357000256,
+                                    "count": 133823,
+                                    "self": 591.9375252000257,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 1.4084104999999454,
+                                            "count": 4,
+                                            "self": 1.4084104999999454
+                                        }
+                                    }
                                 },
                                 "_update_policy": {
-                                    "total": 131.74585990000003,
-                                    "count": 4,
-                                    "self": 16.427197800000172,
+                                    "total": 2968.3630170000006,
+                                    "count": 95,
+                                    "self": 346.12241280002763,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 115.31866209999986,
-                                            "count": 129,
-                                            "self": 115.31866209999986
+                                            "total": 2622.240604199973,
+                                            "count": 2856,
+                                            "self": 2622.240604199973
                                         }
                                     }
                                 }
@@ -339,19 +346,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.2999999512430804e-06,
+                    "total": 1.2000000424450263e-06,
                     "count": 1,
-                    "self": 1.2999999512430804e-06
+                    "self": 1.2000000424450263e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.44806330000000116,
+                    "total": 0.31665739999971265,
                     "count": 1,
-                    "self": 0.009192299999995157,
+                    "self": 0.03600859999914974,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.438871000000006,
+                            "total": 0.2806488000005629,
                             "count": 1,
-                            "self": 0.438871000000006
+                            "self": 0.2806488000005629
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,24 +1,60 @@
 {
     "SoccerTwos": {
-        "elo": 1199.0399471383985,
         "checkpoints": [
             {
-                "steps": 101618,
-                "file_path": "results\\SoccerTwos100kc\\SoccerTwos\\SoccerTwos-101618.onnx",
+                "steps": 499248,
+                "file_path": "results\\SoccerTwos2Ma\\SoccerTwos\\SoccerTwos-499248.onnx",
                 "reward": 0.0,
-                "creation_time": 1678304075.926455,
+                "creation_time": 1678306449.0381513,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos100kc\\SoccerTwos\\SoccerTwos-101618.pt"
+                    "results\\SoccerTwos2Ma\\SoccerTwos\\SoccerTwos-499248.pt"
+                ]
+            },
+            {
+                "steps": 999955,
+                "file_path": "results\\SoccerTwos2Ma\\SoccerTwos\\SoccerTwos-999955.onnx",
+                "reward": 0.0,
+                "creation_time": 1678308118.9153037,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos2Ma\\SoccerTwos\\SoccerTwos-999955.pt"
+                ]
+            },
+            {
+                "steps": 1499832,
+                "file_path": "results\\SoccerTwos2Ma\\SoccerTwos\\SoccerTwos-1499832.onnx",
+                "reward": 0.0,
+                "creation_time": 1678309925.767637,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos2Ma\\SoccerTwos\\SoccerTwos-1499832.pt"
+                ]
+            },
+            {
+                "steps": 1999990,
+                "file_path": "results\\SoccerTwos2Ma\\SoccerTwos\\SoccerTwos-1999990.onnx",
+                "reward": 0.0,
+                "creation_time": 1678311716.8404858,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos2Ma\\SoccerTwos\\SoccerTwos-1999990.pt"
+                ]
+            },
+            {
+                "steps": 2000062,
+                "file_path": "results\\SoccerTwos2Ma\\SoccerTwos\\SoccerTwos-2000062.onnx",
+                "reward": 0.0,
+                "creation_time": 1678311717.1524253,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos2Ma\\SoccerTwos\\SoccerTwos-2000062.pt"
                 ]
             }
         ],
+        "elo": 1498.919863184509,
         "final_checkpoint": {
-            "steps": 101618,
-            "file_path": "results\\SoccerTwos100kc\\SoccerTwos.onnx",
+            "steps": 2000062,
+            "file_path": "results\\SoccerTwos2Ma\\SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1678304075.926455,
+            "creation_time": 1678311717.1524253,
             "auxillary_file_paths": [
-                "results\\SoccerTwos100kc\\SoccerTwos\\SoccerTwos-101618.pt"
+                "results\\SoccerTwos2Ma\\SoccerTwos\\SoccerTwos-2000062.pt"
             ]
         }
     },