4th Push

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cffc9d1069ffaaff6fc4962e9ec09ab851e59120bfa6f872a4d6f2348183f7b6
+oid sha256:15f419901bd6fe39abfce10763e28bc52d4ce7a9c591109ecae27a9cb6f5cc51
 size 1764633

SoccerTwos/SoccerTwos-45499926.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:199cc0e251475cfa998fe46eb8e21b04fc0e52b555da9ed2273d2237801ad02f
-size 1764633

SoccerTwos/SoccerTwos-45499926.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2cd619037e6f1e5568e9fa47e2dd86de8a4ed22195a2e6839318dca808a6fbad
-size 28421201

SoccerTwos/{SoccerTwos-43499970.onnx → SoccerTwos-48499956.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:238c4ce043ee615bdca651032e7c1dd3f3f8d6271d8f8c0aa2029c9ed7b9532c
+oid sha256:3cfe16a90acaeac452d66c5c3f1e4c8e96b6fe4e747f0a106199e78e51d19f4f
 size 1764633

SoccerTwos/{SoccerTwos-44499988.pt → SoccerTwos-48499956.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21f9084d046226ed928a78126d4f2a70de62fc8d1091bc99016a526ae775aa9d
+oid sha256:b10eaa22e50e6d6cd9aade274fe6acf263f75888d009f505edc6ecbb71678cbe
 size 28421201

SoccerTwos/{SoccerTwos-44499988.onnx → SoccerTwos-48999726.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67d902dca0d72b18f2477f77aa07387fc90ba908a52d76cb37843a7a0801ec50
+oid sha256:dfd80d020f0fded771f68ac1fbd02576ec3ac6e069bc5cd35ffdc26ff6a0b79e
 size 1764633

SoccerTwos/{SoccerTwos-43499970.pt → SoccerTwos-48999726.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4bae9d4c180950f6f1adf6b5d43d4d450a0cd58e23f46f21ab67461daf66e23
+oid sha256:90736c154d7606e752689e2370afd36d7a60a8a18b5c44334a68364aa6b57c5d
 size 28421201

SoccerTwos/{SoccerTwos-43999996.onnx → SoccerTwos-49499964.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:557e054b41fbb5f33f156d4bacdae95ce4e3bbe817d757dffefd85f0fc5afc36
+oid sha256:0add5e21e2aa88b1ed424276093d3f76903e8e428dd9e3da501a4b0b22550633
 size 1764633

SoccerTwos/{SoccerTwos-44999999.pt → SoccerTwos-49499964.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3f29cfaba5352cb0730c7d5062657ff08d8c26dd8af8d70b0c8ef2136e1aad1
+oid sha256:384767f00ab4de1b832c3fa97612f522fac9094a2e85da7103d65d5e049a04b2
 size 28421201

SoccerTwos/{SoccerTwos-44999999.onnx → SoccerTwos-49999988.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f6b95d12dd47bb87c60b869a47c08a2bbea6c733d53fa99786fce15ded7798b
+oid sha256:15f419901bd6fe39abfce10763e28bc52d4ce7a9c591109ecae27a9cb6f5cc51
 size 1764633

SoccerTwos/{SoccerTwos-43999996.pt → SoccerTwos-49999988.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:652994fffd1dc978e3c745ccbcc4702afbcaf2f7e9bb9ae520b212891e514098
+oid sha256:7db1dcaf3382ccd614b980cbb727dd1b58d139c1c9d49e152fc83ca4be69b391
 size 28421201

SoccerTwos/SoccerTwos-50000040.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15f419901bd6fe39abfce10763e28bc52d4ce7a9c591109ecae27a9cb6f5cc51
+size 1764633

SoccerTwos/SoccerTwos-50000040.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ff9cc52b3203a139c06135021a7d6bfe54c23d72bc1479e7eda2f59def8ae32
+size 28421201

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cd619037e6f1e5568e9fa47e2dd86de8a4ed22195a2e6839318dca808a6fbad
+oid sha256:4ff9cc52b3203a139c06135021a7d6bfe54c23d72bc1479e7eda2f59def8ae32
 size 28421201

SoccerTwos/events.out.tfevents.1676069007.BigMac.local.1228.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6785f4ee9eb76869adcc4b9ac4850b5a6a5d741fc8cac88c06a0f182cde8bce9
-size 43837439
+oid sha256:2235e54cdbf15d96fb1b864b8f82b3fe00747734d71c8fed868b1aed6a9940e6
+size 48030827

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": 50000000, "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": "./training-envs-executables/SoccerTwos", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": 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": 50000000, "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": "./training-envs-executables/SoccerTwos", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -72,8 +72,8 @@ checkpoint_settings:
   run_id: SoccerTwos
   initialize_from: null
   load_model: false
-  resume: true
-  force: false
+  resume: false
+  force: true
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -2794,3 +2794,240 @@ TOO LONG
 TOO LONG
 TOO LONG
 TOO LONG
+Setting up 3 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]: 945759 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
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 131 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 78.8 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 3
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 5
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_OSX HID Input]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.7 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 5
+    [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]: 945760 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.8 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 945760 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.8 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 945759 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]: 945760 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 173.5 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 945760 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]: 945759 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 3.4 MB
+      Peak Large allocation bytes 0 B
+[ALLOC_TYPETREE] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 945760 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]: 945759 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
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -1,45 +1,364 @@
 {
     "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 1.4963933229446411,
+            "min": 1.408483624458313,
+            "max": 3.29571270942688,
+            "count": 5000
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 29353.251953125,
+            "min": 17898.99609375,
+            "max": 129690.0234375,
+            "count": 5000
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 64.85526315789474,
+            "min": 48.93,
+            "max": 999.0,
+            "count": 5000
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19716.0,
+            "min": 16320.0,
+            "max": 23548.0,
+            "count": 5000
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1986.2290766666756,
+            "min": 1196.4713145206497,
+            "max": 2035.545787867456,
+            "count": 4718
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 301906.8196533347,
+            "min": 2395.5018840418998,
+            "max": 389188.2794481589,
+            "count": 4718
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 49999988.0,
+            "min": 9760.0,
+            "max": 49999988.0,
+            "count": 5000
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 49999988.0,
+            "min": 9760.0,
+            "max": 49999988.0,
+            "count": 5000
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.01866314746439457,
+            "min": -0.14000248908996582,
+            "max": 0.12597665190696716,
+            "count": 5000
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -2.8367984294891357,
+            "min": -22.540401458740234,
+            "max": 16.092144012451172,
+            "count": 5000
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.018723903223872185,
+            "min": -0.14310425519943237,
+            "max": 0.1285843402147293,
+            "count": 5000
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -2.8460333347320557,
+            "min": -22.094587326049805,
+            "max": 16.1998348236084,
+            "count": 5000
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 5000
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 5000
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.03278157899254247,
+            "min": -0.6470588235294118,
+            "max": 0.5818533301353455,
+            "count": 5000
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -4.982800006866455,
+            "min": -62.61580002307892,
+            "max": 53.87600004673004,
+            "count": 5000
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.03278157899254247,
+            "min": -0.6470588235294118,
+            "max": 0.5818533301353455,
+            "count": 5000
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -4.982800006866455,
+            "min": -62.61580002307892,
+            "max": 53.87600004673004,
+            "count": 5000
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 5000
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 5000
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.01672766050323844,
+            "min": 0.010218130899981285,
+            "max": 0.026053640067887802,
+            "count": 2409
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.01672766050323844,
+            "min": 0.010218130899981285,
+            "max": 0.026053640067887802,
+            "count": 2409
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.10420755222439766,
+            "min": 2.20016370307737e-09,
+            "max": 0.10751013110081355,
+            "count": 2409
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.10420755222439766,
+            "min": 2.20016370307737e-09,
+            "max": 0.10751013110081355,
+            "count": 2409
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.10512582957744598,
+            "min": 2.462296692466263e-09,
+            "max": 0.1082919495801131,
+            "count": 2409
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.10512582957744598,
+            "min": 2.462296692466263e-09,
+            "max": 0.1082919495801131,
+            "count": 2409
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 2409
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 2409
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 2409
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 2409
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 2409
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 2409
+        }
+    },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1676068972",
+        "start_time_seconds": "1676069006",
         "python_version": "3.9.16 (main, Jan 11 2023, 10:02:19) \n[Clang 14.0.6 ]",
-        "command_line_arguments": "/Users/ivanchistyakov/Desktop/ml-agents/ml-agents/mlagents/trainers/learn.py ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos --run-id=SoccerTwos --no-graphics --resume",
+        "command_line_arguments": "/Users/ivanchistyakov/Desktop/ml-agents/ml-agents/mlagents/trainers/learn.py ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos --run-id=SoccerTwos --no-graphics --force",
         "mlagents_version": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1676068974"
+        "end_time_seconds": "1676391259"
     },
-    "total": 2.225930589,
+    "total": 322242.644030672,
     "count": 1,
-    "self": 0.35625418799999964,
+    "self": 0.3279518609633669,
     "children": {
         "run_training.setup": {
-            "total": 0.028160181999999923,
+            "total": 0.016999580000000014,
             "count": 1,
-            "self": 0.028160181999999923
+            "self": 0.016999580000000014
         },
         "TrainerController.start_learning": {
-            "total": 1.8415162190000003,
+            "total": 322242.299079231,
             "count": 1,
-            "self": 6.675400000011322e-05,
+            "self": 59.97265928611159,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 1.663341053,
+                    "total": 6.2347968669171685,
+                    "count": 250,
+                    "self": 6.2347968669171685
+                },
+                "TrainerController.advance": {
+                    "total": 322175.92392550997,
+                    "count": 3376647,
+                    "self": 63.354187416203786,
+                    "children": {
+                        "env_step": {
+                            "total": 42838.97478724331,
+                            "count": 3376647,
+                            "self": 34941.08387098866,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 7858.295024526432,
+                                    "count": 3376647,
+                                    "self": 333.92455918631913,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 7524.370465340113,
+                                            "count": 6305168,
+                                            "self": 7524.370465340113
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 39.59589172821464,
+                                    "count": 3376647,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 322142.54228148673,
+                                            "count": 3376647,
+                                            "is_parallel": true,
+                                            "self": 294074.76907246886,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.3860330660266218,
+                                                    "count": 500,
+                                                    "is_parallel": true,
+                                                    "self": 0.0781055047419148,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.307927561284707,
+                                                            "count": 2000,
+                                                            "is_parallel": true,
+                                                            "self": 0.307927561284707
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 28067.38717595182,
+                                                    "count": 3376647,
+                                                    "is_parallel": true,
+                                                    "self": 1689.5224428774309,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 1064.3330249926516,
+                                                            "count": 3376647,
+                                                            "is_parallel": true,
+                                                            "self": 1064.3330249926516
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 20361.388769087243,
+                                                            "count": 3376647,
+                                                            "is_parallel": true,
+                                                            "self": 20361.388769087243
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 4952.142938994494,
+                                                            "count": 6753294,
+                                                            "is_parallel": true,
+                                                            "self": 1010.4682478903151,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 3941.674691104179,
+                                                                    "count": 27013176,
+                                                                    "is_parallel": true,
+                                                                    "self": 3941.674691104179
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 279273.5949508505,
+                            "count": 3376647,
+                            "self": 435.3135163091356,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 12910.544843309937,
+                                    "count": 3376647,
+                                    "self": 12890.749638091116,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 19.79520521882091,
+                                            "count": 100,
+                                            "self": 19.79520521882091
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 265927.73659123137,
+                                    "count": 2409,
+                                    "self": 6506.972498562565,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 259420.7640926688,
+                                            "count": 72270,
+                                            "self": 259420.7640926688
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 7.500057108700275e-07,
                     "count": 1,
-                    "self": 1.663341053
+                    "self": 7.500057108700275e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.17810841200000027,
+                    "total": 0.16769681801088154,
                     "count": 1,
-                    "self": 0.0010308110000001314,
+                    "self": 0.0011068930034525692,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.17707760100000014,
+                            "total": 0.16658992500742897,
                             "count": 1,
-                            "self": 0.17707760100000014
+                            "self": 0.16658992500742897
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,30 +1,66 @@
 {
-    "metadata": {
-        "stats_format_version": "0.3.0",
-        "mlagents_version": "0.31.0.dev0",
-        "torch_version": "1.11.0"
-    },
     "SoccerTwos": {
-        "elo": 1200.0,
         "checkpoints": [
             {
-                "steps": 0,
-                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-0.onnx",
-                "reward": null,
-                "creation_time": 1676068974.5930471,
+                "steps": 48499956,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-48499956.onnx",
+                "reward": 0.0,
+                "creation_time": 1676378432.911664,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-48499956.pt"
+                ]
+            },
+            {
+                "steps": 48999726,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-48999726.onnx",
+                "reward": 0.0,
+                "creation_time": 1676382674.299469,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-48999726.pt"
+                ]
+            },
+            {
+                "steps": 49499964,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-49499964.onnx",
+                "reward": 0.0,
+                "creation_time": 1676386912.843196,
                 "auxillary_file_paths": [
-                    "results/SoccerTwos/SoccerTwos/SoccerTwos-0.pt"
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-49499964.pt"
+                ]
+            },
+            {
+                "steps": 49999988,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-49999988.onnx",
+                "reward": 0.0,
+                "creation_time": 1676391258.793409,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-49999988.pt"
+                ]
+            },
+            {
+                "steps": 50000040,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-50000040.onnx",
+                "reward": 0.0,
+                "creation_time": 1676391258.977122,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-50000040.pt"
                 ]
             }
         ],
+        "elo": 1987.9038214734514,
         "final_checkpoint": {
-            "steps": 0,
+            "steps": 50000040,
             "file_path": "results/SoccerTwos/SoccerTwos.onnx",
-            "reward": null,
-            "creation_time": 1676068974.5930471,
+            "reward": 0.0,
+            "creation_time": 1676391258.977122,
             "auxillary_file_paths": [
-                "results/SoccerTwos/SoccerTwos/SoccerTwos-0.pt"
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-50000040.pt"
             ]
         }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0"
     }
 }