5`

SoccerTwos - Copy.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39c65074cedaf4ca152682deb12d752e2baec90f2e899ec11749e18212e94461
+size 1768746

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89f774c7a87e8ecc70021639a544e1cd962edb913974c0afebd20f042fa59c81
-size 891095
+oid sha256:9d2a3147e5faa704209294c2285052c3c75488748b6fbe72ccd542e422bae028
+size 1768746

SoccerTwos/SoccerTwos-10000032.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d2a3147e5faa704209294c2285052c3c75488748b6fbe72ccd542e422bae028
+size 1768746

SoccerTwos/SoccerTwos-10000032.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dd9153c840f97752d159fbc6e3bb46f5f1477315b11e040beb978b3f29bef2f
+size 28431689

SoccerTwos/SoccerTwos-8499991.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:046f60611dc38663e53fa2a88ef4cd6b427177d99aa745b1494bd5feeb3350a8
+size 1768746

SoccerTwos/SoccerTwos-8499991.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:936982297e1f32aa24066a90a022609182347468e301ed2e6cb759250eb79e9b
+size 28431567

SoccerTwos/SoccerTwos-8999947.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbefd008bd123b56be604ddd70daf23f4683d14a80439b4ba94bb836798a91ff
+size 1768746

SoccerTwos/SoccerTwos-8999947.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4518d726d9497589b99b97f188b3db01e40575f9b1a84007598c29df1e51f8da
+size 28431567

SoccerTwos/SoccerTwos-9499967.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad0c48b709e91f849419d05dabed627ba8c5f43951ed51d4c02530ef7a90c816
+size 1768746

SoccerTwos/SoccerTwos-9499967.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c05cffaa5d99500ff55c5679efddd7c79ee694514aab2b8831505fbcec9ea693
+size 28431567

SoccerTwos/SoccerTwos-9999972.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d2a3147e5faa704209294c2285052c3c75488748b6fbe72ccd542e422bae028
+size 1768746

SoccerTwos/SoccerTwos-9999972.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb348ed051b020291efa973012b4b2d5bdbd9da478c666dd5c46a05320ddc393
+size 28431567

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6b21cce0fe52f3dd90446c4ce55a969983f295f0c098956e46932e94f2b8f88
-size 10313871
+oid sha256:4b6849b0320d943eebdad08c7a7e46300225e96949950a859fbddad915911a12
+size 28430591

SoccerTwos/events.out.tfevents.1694212696.voyz-laptop.16860.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:583df27e2588c1cf7801f4d893d2fc02f7782e132575f89c539ee6b37b638aef
+size 4633251

SoccerTwos/events.out.tfevents.1694236464.voyz-laptop.19060.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64c5a5e2779105080f2c99865b040f1f1a361a9060b48ebab6ab3f008c52583c
+size 5140315

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": 0.93, "num_epoch": 4, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.975, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 100000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 40000, "team_change": 100000, "swap_steps": 1000, "window": 10, "play_against_latest_model_ratio": 0.4, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./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": "SoccerTwos2", "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": 3000, "buffer_size": 20480, "learning_rate": 0.0002, "beta": 0.004, "epsilon": 0.25, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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": 0.985, "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": 10000000, "time_horizon": 800, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 75000, "team_change": 300000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.55, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./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": "SoccerTwos5", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -3,28 +3,28 @@ behaviors:
   SoccerTwos:
     trainer_type: poca
     hyperparameters:
-      batch_size: 2048
+      batch_size: 3000
       buffer_size: 20480
-      learning_rate: 0.0003
-      beta: 0.005
-      epsilon: 0.2
-      lambd: 0.93
-      num_epoch: 4
-      learning_rate_schedule: constant
-      beta_schedule: constant
-      epsilon_schedule: constant
+      learning_rate: 0.0002
+      beta: 0.004
+      epsilon: 0.25
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
     checkpoint_interval: 500000
     network_settings:
       normalize: false
-      hidden_units: 256
-      num_layers: 3
+      hidden_units: 512
+      num_layers: 2
       vis_encode_type: simple
       memory: null
       goal_conditioning_type: hyper
       deterministic: false
     reward_signals:
       extrinsic:
-        gamma: 0.975
+        gamma: 0.985
         strength: 1.0
         network_settings:
           normalize: false
@@ -37,16 +37,16 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 100000
-    time_horizon: 1000
+    max_steps: 10000000
+    time_horizon: 800
     summary_freq: 10000
     threaded: false
     self_play:
-      save_steps: 40000
-      team_change: 100000
-      swap_steps: 1000
+      save_steps: 75000
+      team_change: 300000
+      swap_steps: 2000
       window: 10
-      play_against_latest_model_ratio: 0.4
+      play_against_latest_model_ratio: 0.55
       initial_elo: 1200.0
     behavioral_cloning: null
 env_settings:
@@ -69,10 +69,10 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: SoccerTwos2
+  run_id: SoccerTwos5
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -9,7 +9,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.275 seconds
+- Completed reload, in  0.283 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)
@@ -35,48 +35,15 @@ 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: 1.217800 ms
+UnloadTime: 1.011700 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-TOO LONG
-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]: 1992 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 93928 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
@@ -104,7 +71,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 0]
       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_Background Job.Worker 10]
       Initial Block Size 32.0 KB
@@ -139,7 +106,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 3]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 0.8 KB
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -242,22 +209,22 @@ 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 3
     [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]: 1993 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 93929 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.3 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]: 1993 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 93929 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.1 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
@@ -286,13 +253,13 @@ 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]: 1992 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 93928 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]: 1993 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 93929 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.6 KB
@@ -304,16 +271,16 @@ 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]: 1993 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 93929 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]: 1992 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 93928 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
+      Peak Allocated memory 3.2 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
@@ -322,13 +289,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 1993 frames
+      Peak usage frame count: [0-1.0 KB]: 93929 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]: 1992 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 93928 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": 3.276162624359131,
-            "min": 3.276162624359131,
-            "max": 3.2958109378814697,
-            "count": 10
+            "value": 1.4813734292984009,
+            "min": 1.4523465633392334,
+            "max": 1.8827192783355713,
+            "count": 500
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 63321.671875,
-            "min": 31877.875,
-            "max": 108735.390625,
-            "count": 10
+            "value": 30291.123046875,
+            "min": 27888.0,
+            "max": 40787.23046875,
+            "count": 500
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 871.3333333333334,
-            "min": 578.4,
-            "max": 957.6,
-            "count": 10
+            "value": 42.61739130434783,
+            "min": 35.40875912408759,
+            "max": 62.2125,
+            "count": 500
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 20912.0,
-            "min": 17044.0,
-            "max": 23136.0,
-            "count": 10
+            "value": 19604.0,
+            "min": 18192.0,
+            "max": 20496.0,
+            "count": 500
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1205.605042435029,
-            "min": 1199.3846093194823,
-            "max": 1205.605042435029,
-            "count": 10
+            "value": 1577.3278964698527,
+            "min": 1505.856633164282,
+            "max": 1607.9342147062453,
+            "count": 500
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 4822.420169740116,
-            "min": 2408.238853024137,
-            "max": 19190.153749111716,
-            "count": 10
+            "value": 362785.4161880661,
+            "min": 241869.99428611956,
+            "max": 428521.8946358607,
+            "count": 500
         },
         "SoccerTwos.Step.mean": {
-            "value": 99052.0,
-            "min": 9588.0,
-            "max": 99052.0,
-            "count": 10
+            "value": 9999972.0,
+            "min": 5009954.0,
+            "max": 9999972.0,
+            "count": 500
         },
         "SoccerTwos.Step.sum": {
-            "value": 99052.0,
-            "min": 9588.0,
-            "max": 99052.0,
-            "count": 10
+            "value": 9999972.0,
+            "min": 5009954.0,
+            "max": 9999972.0,
+            "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.04067975655198097,
-            "min": -0.14784616231918335,
-            "max": -0.04067975655198097,
-            "count": 10
+            "value": -0.016964344307780266,
+            "min": -0.09779278188943863,
+            "max": 0.09828563779592514,
+            "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -0.4474773108959198,
-            "min": -2.66123104095459,
-            "max": -0.4474773108959198,
-            "count": 10
+            "value": -3.901799201965332,
+            "min": -22.003376007080078,
+            "max": 20.639984130859375,
+            "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.03995228931307793,
-            "min": -0.1478474885225296,
-            "max": -0.03995228931307793,
-            "count": 10
+            "value": -0.01681143417954445,
+            "min": -0.09867770969867706,
+            "max": 0.09790761768817902,
+            "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -0.4394751787185669,
-            "min": -2.6612548828125,
-            "max": -0.4394751787185669,
-            "count": 10
+            "value": -3.8666298389434814,
+            "min": -22.202484130859375,
+            "max": 20.56060028076172,
+            "count": 500
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 10
+            "count": 500
         },
         "SoccerTwos.Environment.CumulativeReward.sum": {
             "value": 0.0,
             "min": 0.0,
             "max": 0.0,
-            "count": 10
+            "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": 0.13941818475723267,
-            "min": -0.3098222215970357,
-            "max": 0.27174285479954313,
-            "count": 10
+            "value": -0.018830435431521873,
+            "min": -0.28656395542067153,
+            "max": 0.254424856207465,
+            "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": 1.5336000323295593,
-            "min": -5.576799988746643,
-            "max": 3.8043999671936035,
-            "count": 10
+            "value": -4.3310001492500305,
+            "min": -57.68040007352829,
+            "max": 50.397399604320526,
+            "count": 500
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": 0.13941818475723267,
-            "min": -0.3098222215970357,
-            "max": 0.27174285479954313,
-            "count": 10
+            "value": -0.018830435431521873,
+            "min": -0.28656395542067153,
+            "max": 0.254424856207465,
+            "count": 500
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": 1.5336000323295593,
-            "min": -5.576799988746643,
-            "max": 3.8043999671936035,
-            "count": 10
+            "value": -4.3310001492500305,
+            "min": -57.68040007352829,
+            "max": 50.397399604320526,
+            "count": 500
         },
         "SoccerTwos.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 10
+            "count": 500
         },
         "SoccerTwos.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 10
+            "count": 500
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.01526298027993107,
-            "min": 0.01099250649131136,
-            "max": 0.018091706759878434,
-            "count": 4
+            "value": 0.014714702679258253,
+            "min": 0.008386772028138189,
+            "max": 0.021870147617947724,
+            "count": 243
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.01526298027993107,
-            "min": 0.01099250649131136,
-            "max": 0.018091706759878434,
-            "count": 4
+            "value": 0.014714702679258253,
+            "min": 0.008386772028138189,
+            "max": 0.021870147617947724,
+            "count": 243
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.002327583177248016,
-            "min": 0.0014520563257974573,
-            "max": 0.0041336810740176585,
-            "count": 4
+            "value": 0.12173405372434193,
+            "min": 0.10558312717411253,
+            "max": 0.13476302888658312,
+            "count": 243
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.002327583177248016,
-            "min": 0.0014520563257974573,
-            "max": 0.0041336810740176585,
-            "count": 4
+            "value": 0.12173405372434193,
+            "min": 0.10558312717411253,
+            "max": 0.13476302888658312,
+            "count": 243
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.002341294757206924,
-            "min": 0.0014541281125275418,
-            "max": 0.004133668169379235,
-            "count": 4
+            "value": 0.12211715016100141,
+            "min": 0.10619260908828841,
+            "max": 0.13504979014396667,
+            "count": 243
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.002341294757206924,
-            "min": 0.0014541281125275418,
-            "max": 0.004133668169379235,
-            "count": 4
+            "value": 0.12211715016100141,
+            "min": 0.10619260908828841,
+            "max": 0.13504979014396667,
+            "count": 243
         },
         "SoccerTwos.Policy.LearningRate.mean": {
-            "value": 0.0003,
-            "min": 0.0003,
-            "max": 0.0003,
-            "count": 4
+            "value": 6.921996543998919e-08,
+            "min": 6.921996543998919e-08,
+            "max": 9.958629020688e-05,
+            "count": 243
         },
         "SoccerTwos.Policy.LearningRate.sum": {
-            "value": 0.0003,
-            "min": 0.0003,
-            "max": 0.0003,
-            "count": 4
+            "value": 6.921996543998919e-08,
+            "min": 6.921996543998919e-08,
+            "max": 9.958629020688e-05,
+            "count": 243
         },
         "SoccerTwos.Policy.Epsilon.mean": {
-            "value": 0.2,
-            "min": 0.2,
-            "max": 0.2,
-            "count": 4
+            "value": 0.10005183999999999,
+            "min": 0.10005183999999999,
+            "max": 0.17468968000000004,
+            "count": 243
         },
         "SoccerTwos.Policy.Epsilon.sum": {
-            "value": 0.2,
-            "min": 0.2,
-            "max": 0.2,
-            "count": 4
+            "value": 0.10005183999999999,
+            "min": 0.10005183999999999,
+            "max": 0.17468968000000004,
+            "count": 243
         },
         "SoccerTwos.Policy.Beta.mean": {
-            "value": 0.005,
-            "min": 0.005,
-            "max": 0.005,
-            "count": 4
+            "value": 1.1378943999999786e-05,
+            "min": 1.1378943999999786e-05,
+            "max": 0.001996745488000001,
+            "count": 243
         },
         "SoccerTwos.Policy.Beta.sum": {
-            "value": 0.005,
-            "min": 0.005,
-            "max": 0.005,
-            "count": 4
+            "value": 1.1378943999999786e-05,
+            "min": 1.1378943999999786e-05,
+            "max": 0.001996745488000001,
+            "count": 243
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1694200051",
+        "start_time_seconds": "1694236457",
         "python_version": "3.9.13 (tags/v3.9.13:6de2ca5, May 17 2022, 16:36:42) [MSC v.1929 64 bit (AMD64)]",
-        "command_line_arguments": "C:\\Users\\voyz\\.virtualenvs\\deep_rl_course_u7_p39\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos2 --no-graphics",
+        "command_line_arguments": "C:\\Users\\voyz\\.virtualenvs\\deep_rl_course_u7_p39\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos5 --no-graphics --resume",
         "mlagents_version": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.0.1+cu118",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1694200514"
+        "end_time_seconds": "1694258857"
     },
-    "total": 462.8447187,
+    "total": 22401.2324006,
     "count": 1,
-    "self": 0.5600668999999812,
+    "self": 0.5248601000021154,
     "children": {
         "run_training.setup": {
-            "total": 0.2883186000000002,
+            "total": 0.24669090000000082,
             "count": 1,
-            "self": 0.2883186000000002
+            "self": 0.24669090000000082
         },
         "TrainerController.start_learning": {
-            "total": 461.9963332,
+            "total": 22400.4608496,
             "count": 1,
-            "self": 0.26809090000108426,
+            "self": 12.748866300415102,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 11.783397300000004,
-                    "count": 2,
-                    "self": 11.783397300000004
+                    "total": 10.469387500001687,
+                    "count": 18,
+                    "self": 10.469387500001687
                 },
                 "TrainerController.advance": {
-                    "total": 449.4835636999989,
-                    "count": 6693,
-                    "self": 0.3020811999973603,
+                    "total": 22376.872806599582,
+                    "count": 356113,
+                    "self": 12.226129598384432,
                     "children": {
                         "env_step": {
-                            "total": 362.56483840000067,
-                            "count": 6693,
-                            "self": 210.9430835000013,
+                            "total": 16583.080249001483,
+                            "count": 356113,
+                            "self": 10007.274636201531,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 151.45439609999883,
-                                    "count": 6693,
-                                    "self": 1.9777616999990641,
+                                    "total": 6568.347290199748,
+                                    "count": 356113,
+                                    "self": 83.64209400055552,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 149.47663439999977,
-                                            "count": 13284,
-                                            "self": 149.47663439999977
+                                            "total": 6484.705196199193,
+                                            "count": 626198,
+                                            "self": 6484.705196199193
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.16735880000053527,
-                                    "count": 6693,
+                                    "total": 7.458322600202077,
+                                    "count": 356113,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 451.6781600000008,
-                                            "count": 6693,
+                                            "total": 22370.41648019894,
+                                            "count": 356113,
                                             "is_parallel": true,
-                                            "self": 275.8103001000021,
+                                            "self": 13851.782743698908,
                                             "children": {
                                                 "steps_from_proto": {
-                                                    "total": 0.0030068999999990353,
-                                                    "count": 2,
+                                                    "total": 0.05337660000131006,
+                                                    "count": 36,
                                                     "is_parallel": true,
-                                                    "self": 0.0006187999999962557,
+                                                    "self": 0.011230800010800124,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.0023881000000027797,
-                                                            "count": 8,
+                                                            "total": 0.042145799990509936,
+                                                            "count": 144,
                                                             "is_parallel": true,
-                                                            "self": 0.0023881000000027797
+                                                            "self": 0.042145799990509936
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 175.86485299999867,
-                                                    "count": 6693,
+                                                    "total": 8518.58035990003,
+                                                    "count": 356113,
                                                     "is_parallel": true,
-                                                    "self": 8.184614699993176,
+                                                    "self": 328.68323039905226,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 6.472482399999393,
-                                                            "count": 6693,
+                                                            "total": 233.64260100085235,
+                                                            "count": 356113,
                                                             "is_parallel": true,
-                                                            "self": 6.472482399999393
+                                                            "self": 233.64260100085235
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 134.8811544000017,
-                                                            "count": 6693,
+                                                            "total": 6884.315014400223,
+                                                            "count": 356113,
                                                             "is_parallel": true,
-                                                            "self": 134.8811544000017
+                                                            "self": 6884.315014400223
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 26.32660150000443,
-                                                            "count": 13386,
+                                                            "total": 1071.9395140999022,
+                                                            "count": 712226,
                                                             "is_parallel": true,
-                                                            "self": 5.451002400006839,
+                                                            "self": 230.18878070043002,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 20.87559909999759,
-                                                                    "count": 53544,
+                                                                    "total": 841.7507333994722,
+                                                                    "count": 2848904,
                                                                     "is_parallel": true,
-                                                                    "self": 20.87559909999759
+                                                                    "self": 841.7507333994722
                                                                 }
                                                             }
                                                         }
@@ -313,24 +313,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 86.61664410000088,
-                            "count": 6693,
-                            "self": 1.6339948000024407,
+                            "total": 5781.5664279997145,
+                            "count": 356113,
+                            "self": 79.6152038996297,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 20.554220999998492,
-                                    "count": 6693,
-                                    "self": 20.554220999998492
+                                    "total": 3739.4091631001056,
+                                    "count": 356113,
+                                    "self": 3735.5494080001117,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 3.8597550999938903,
+                                            "count": 10,
+                                            "self": 3.8597550999938903
+                                        }
+                                    }
                                 },
                                 "_update_policy": {
-                                    "total": 64.42842829999995,
-                                    "count": 4,
-                                    "self": 40.166855899999845,
+                                    "total": 1962.542060999979,
+                                    "count": 243,
+                                    "self": 1257.5645117999559,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 24.261572400000105,
-                                            "count": 160,
-                                            "self": 24.261572400000105
+                                            "total": 704.9775492000231,
+                                            "count": 4377,
+                                            "self": 704.9775492000231
                                         }
                                     }
                                 }
@@ -339,19 +346,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.1999999856016075e-06,
+                    "total": 1.2000018614344299e-06,
                     "count": 1,
-                    "self": 1.1999999856016075e-06
+                    "self": 1.2000018614344299e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.4612801000000104,
+                    "total": 0.36978799999997136,
                     "count": 1,
-                    "self": 0.006412699999998495,
+                    "self": 0.007586499999888474,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.4548674000000119,
+                            "total": 0.3622015000000829,
                             "count": 1,
-                            "self": 0.4548674000000119
+                            "self": 0.3622015000000829
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,24 +1,60 @@
 {
     "SoccerTwos": {
-        "elo": 1205.726628357257,
         "checkpoints": [
             {
-                "steps": 101052,
-                "file_path": "results\\SoccerTwos2\\SoccerTwos\\SoccerTwos-101052.onnx",
+                "steps": 8499991,
+                "file_path": "results\\SoccerTwos5\\SoccerTwos\\SoccerTwos-8499991.onnx",
                 "reward": 0.0,
-                "creation_time": 1694200514.1483324,
+                "creation_time": 1694252103.7523136,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos2\\SoccerTwos\\SoccerTwos-101052.pt"
+                    "results\\SoccerTwos5\\SoccerTwos\\SoccerTwos-8499991.pt"
+                ]
+            },
+            {
+                "steps": 8999947,
+                "file_path": "results\\SoccerTwos5\\SoccerTwos\\SoccerTwos-8999947.onnx",
+                "reward": 0.0,
+                "creation_time": 1694254573.759802,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos5\\SoccerTwos\\SoccerTwos-8999947.pt"
+                ]
+            },
+            {
+                "steps": 9499967,
+                "file_path": "results\\SoccerTwos5\\SoccerTwos\\SoccerTwos-9499967.onnx",
+                "reward": 0.0,
+                "creation_time": 1694256763.8538606,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos5\\SoccerTwos\\SoccerTwos-9499967.pt"
+                ]
+            },
+            {
+                "steps": 9999972,
+                "file_path": "results\\SoccerTwos5\\SoccerTwos\\SoccerTwos-9999972.onnx",
+                "reward": 0.0,
+                "creation_time": 1694258856.8855429,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos5\\SoccerTwos\\SoccerTwos-9999972.pt"
+                ]
+            },
+            {
+                "steps": 10000032,
+                "file_path": "results\\SoccerTwos5\\SoccerTwos\\SoccerTwos-10000032.onnx",
+                "reward": 0.0,
+                "creation_time": 1694258857.276474,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos5\\SoccerTwos\\SoccerTwos-10000032.pt"
                 ]
             }
         ],
+        "elo": 1578.5504816113921,
         "final_checkpoint": {
-            "steps": 101052,
-            "file_path": "results\\SoccerTwos2\\SoccerTwos.onnx",
+            "steps": 10000032,
+            "file_path": "results\\SoccerTwos5\\SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1694200514.1483324,
+            "creation_time": 1694258857.276474,
             "auxillary_file_paths": [
-                "results\\SoccerTwos2\\SoccerTwos\\SoccerTwos-101052.pt"
+                "results\\SoccerTwos5\\SoccerTwos\\SoccerTwos-10000032.pt"
             ]
         }
     },