max steps 20000000

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8fa6554ea9d83bff961002ca3e6d31af94a7bbde4b8f3959d6e2a8c26a841d3
-size 649394
+oid sha256:bfb3af3e9c0f3a09370a25bc4cf0b142ee2b65f1ad569373eb35de990d628506
+size 912920

SnowballTarget/{SnowballTarget-149984.onnx → SnowballTarget-1599976.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52c4ed4a966b9032190d0e55fd0acbd3eddb1181c40dc483361d19c499e8a564
-size 649394
+oid sha256:cbf21a4ffe8a454e0f32ea61ad270c4f82d4508766436e55ee3cb43978f77816
+size 912920

SnowballTarget/{SnowballTarget-149984.pt → SnowballTarget-1599976.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d6599be2b69a279de776ffc2d309cafb3c6036b87827dd3c82d73509aad1916
-size 3867927
+oid sha256:0efce399dd6349b68d270e13fbcb374ddd2c9efb29595c9c7dbca983a88e0f13
+size 5451155

SnowballTarget/{SnowballTarget-49936.onnx → SnowballTarget-1649992.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f708b2efb694287d61b1b4947250b7321caa36efd8296a8405b6be58352736b0
-size 649394
+oid sha256:e094c7573cde4f8a32b76d3fcf20eccee5220fd37a0525d67974b7258154f0df
+size 912920

SnowballTarget/{SnowballTarget-199984.pt → SnowballTarget-1649992.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b2c44c64cd00951c1f41d6477070f3f0a42e70c4cae407a3c756794d52ac1fd
-size 3867927
+oid sha256:ee99c657cef78f8fa1823b4c38a6a603a2dd844b014ba6873b8004462716831e
+size 5451155

SnowballTarget/{SnowballTarget-199984.onnx → SnowballTarget-1699936.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cc8a8a88de46df2e904865425945c931295f40c0a71bbdd71262386709b81d7
-size 649394
+oid sha256:27981e11779ac3da2af5b36d9036d32df6b6135a6408c6c919c365029e7b15fa
+size 912920

SnowballTarget/SnowballTarget-1699936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8be7ce5bb031be30a9f627db304a95843d971d19957a8b37b00eb44efbed426
+size 5451155

SnowballTarget/{SnowballTarget-99960.onnx → SnowballTarget-1749960.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6809ca7b84c84bbb850f1ccc986d1b162efd377d008af5061a54082771e0510f
-size 649394
+oid sha256:f247e8a102607851cb179bde8ba3bae5add61a65284f8a9fb4acdc6aafb95f53
+size 912920

SnowballTarget/SnowballTarget-1749960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9828c8f0740b8b8e3b46f17d7a3d5d15619fc8ec90d79d61555092ba465b5c5e
+size 5451155

SnowballTarget/SnowballTarget-1799984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72ffeff2c70c8cb3fa17f5feef96bfe646e75218a7069a55dcca4bfdb54e204b
+size 912920

SnowballTarget/SnowballTarget-1799984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4525e36d2443c8cae0f3d069cdb5b7bda4a8ec5ffb2c2c793d0a8490d5c6d46
+size 5451155

SnowballTarget/SnowballTarget-1849984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:010ac0b980e143a83a63e16546f559fa93e9f5250c427d0446d60fa5b5462ddd
+size 912920

SnowballTarget/SnowballTarget-1849984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd00f093e122b145e77b7934a96726e6fa93f09494bd87e229c561e5ad756007
+size 5451155

SnowballTarget/SnowballTarget-1899944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1314495ccef4770ea4e895a354b05a585fd362eb714dedc0ffd4729235b966d9
+size 912920

SnowballTarget/SnowballTarget-1899944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:464fb3821f39bf1fb9fa0d8658f7965cb4d04bf0658364e12289766b2e130f2b
+size 5451155

SnowballTarget/SnowballTarget-1949968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16f5789806a65b68feb5362aa472be01109e7fb4c575a2531bea601903b67c42
+size 912920

SnowballTarget/SnowballTarget-1949968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:953ee4972ebb430d5e682f57f2379de1fdbdb51c5fc34af6bb9a726f788d2769
+size 5451155

SnowballTarget/SnowballTarget-1999992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29c44e5222518350504bf11dc5c0aed7449b2a2cb32f6367fbc068259d81051e
+size 912920

SnowballTarget/SnowballTarget-1999992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43295602878956efe845ae71ce78fea316fdf9c6689a470375e12bebaed69fbe
+size 5451155

SnowballTarget/SnowballTarget-2000376.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfb3af3e9c0f3a09370a25bc4cf0b142ee2b65f1ad569373eb35de990d628506
+size 912920

SnowballTarget/SnowballTarget-2000376.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f31d9b0ea482f641244af8a7a907a2547db8286beb6b003195c6187ec476213
+size 5451155

SnowballTarget/SnowballTarget-49936.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:bb71e1b4174214a9d0a0a16fcddb608480913c10547bc238cff52a2f59e47869
-size 3867927

SnowballTarget/SnowballTarget-99960.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:03e748fa93a0f32b3744113cd432dad4b5f5bf735d7978a0d3bf50b999f12b60
-size 3867927

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44e82a0854de3e8a062655ec32ff141e7d63f6af068b834d05ca880cf9bd3b46
-size 3867927
+oid sha256:9f31d9b0ea482f641244af8a7a907a2547db8286beb6b003195c6187ec476213
+size 5451155

SnowballTarget/events.out.tfevents.1673518269.2e755c600c8d.3919.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:934645464a334fa3921672eb7d255a23df1c22dee9b7add1f3e3219a1a5562e6
-size 27783

SnowballTarget/events.out.tfevents.1673520248.2e755c600c8d.12594.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b83b8c441ddcfc0fdd99898dee5be1ee4ca0810a695fa58e146f7f096bb898f7
+size 167916

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 4, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": true, "hidden_units": 256, "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": 10, "checkpoint_interval": 50000, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "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": "SnowballTarget1", "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": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 10, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": true, "hidden_units": 256, "num_layers": 3, "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": 10, "checkpoint_interval": 50000, "max_steps": 2000000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "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": "SnowballTarget1", "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

@@ -9,14 +9,14 @@ behaviors:
       beta: 0.005
       epsilon: 0.2
       lambd: 0.95
-      num_epoch: 4
+      num_epoch: 10
       learning_rate_schedule: linear
       beta_schedule: linear
       epsilon_schedule: linear
     network_settings:
       normalize: true
       hidden_units: 256
-      num_layers: 2
+      num_layers: 3
       vis_encode_type: simple
       memory: null
       goal_conditioning_type: hyper
@@ -36,7 +36,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 10
     checkpoint_interval: 50000
-    max_steps: 200000
+    max_steps: 2000000
     time_horizon: 64
     summary_freq: 10000
     threaded: true
@@ -66,7 +66,7 @@ checkpoint_settings:
   initialize_from: null
   load_model: false
   resume: false
-  force: false
+  force: true
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
 Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
-Unable to load player prefs
 Initialize engine version: 2021.3.14f1 (eee1884e7226)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.075 seconds
+- Completed reload, in  0.077 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -45,7 +42,7 @@ 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: 0.687533 ms
+UnloadTime: 0.617421 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -53,7 +50,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 5371 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 53654 frames, [16.0 KB-32.0 KB]: 909 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
@@ -169,22 +166,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 44
+  Peak main deferred allocation count 48
     [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]: 5463 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 11425 frames, [8.0 MB-16.0 MB]: 27611 frames, [16.0 MB-32.0 MB]: 15528 frames
       Requested Block Size 16.0 MB
-      Peak Block count 1
-      Peak Allocated memory 6.5 MB
+      Peak Block count 2
+      Peak Allocated memory 24.3 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 5463 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 54564 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.8 MB
+      Peak Allocated memory 17.7 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -213,13 +210,13 @@ 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]: 5125 frames, [64.0 KB-128.0 KB]: 338 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 52528 frames, [64.0 KB-128.0 KB]: 2036 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 66.8 KB
+      Peak Allocated memory 67.3 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 5463 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 54564 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -231,13 +228,13 @@ 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]: 5463 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 54564 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]: 5462 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 54563 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
@@ -249,13 +246,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 5463 frames
+      Peak usage frame count: [0-1.0 KB]: 54564 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]: 5463 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 54564 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -2,220 +2,220 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 1.161288857460022,
-            "min": 1.161288857460022,
-            "max": 2.859130620956421,
-            "count": 20
+            "value": 0.5269735455513,
+            "min": 0.5269735455513,
+            "max": 2.8357203006744385,
+            "count": 200
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 11139.0830078125,
-            "min": 11139.0830078125,
-            "max": 29469.05859375,
-            "count": 20
+            "value": 5437.31298828125,
+            "min": 5105.45654296875,
+            "max": 29196.576171875,
+            "count": 200
         },
         "SnowballTarget.Step.mean": {
-            "value": 199984.0,
+            "value": 1999992.0,
             "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+            "max": 1999992.0,
+            "count": 200
         },
         "SnowballTarget.Step.sum": {
-            "value": 199984.0,
+            "value": 1999992.0,
             "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+            "max": 1999992.0,
+            "count": 200
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 13.382231712341309,
-            "min": 0.39233580231666565,
-            "max": 13.382231712341309,
-            "count": 20
+            "value": 15.033926963806152,
+            "min": 0.4628317654132843,
+            "max": 15.097548484802246,
+            "count": 200
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2609.53515625,
-            "min": 76.11314392089844,
-            "max": 2703.5830078125,
-            "count": 20
+            "value": 3081.955078125,
+            "min": 89.78936004638672,
+            "max": 3085.62646484375,
+            "count": 200
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
             "value": 199.0,
             "min": 199.0,
             "max": 199.0,
-            "count": 20
+            "count": 200
         },
         "SnowballTarget.Environment.EpisodeLength.sum": {
             "value": 10945.0,
             "min": 8756.0,
             "max": 10945.0,
-            "count": 20
+            "count": 200
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.07226822885936332,
-            "min": 0.06235124173562166,
-            "max": 0.07426282722521778,
-            "count": 20
+            "value": 0.07078048211322954,
+            "min": 0.06503697658053118,
+            "max": 0.07793410775942475,
+            "count": 200
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.2890729154374533,
-            "min": 0.24940496694248665,
-            "max": 0.36103966150039923,
-            "count": 20
+            "value": 0.3539024105661477,
+            "min": 0.26219758718789843,
+            "max": 0.3824035105034401,
+            "count": 200
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.173360130722251,
-            "min": 0.11157261524674729,
-            "max": 0.3051871352774256,
-            "count": 20
+            "value": 0.11107677399673883,
+            "min": 0.0889188205001547,
+            "max": 0.24954896199352605,
+            "count": 200
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.693440522889004,
-            "min": 0.44629046098698916,
-            "max": 1.3741096786278135,
-            "count": 20
+            "value": 0.5553838699836942,
+            "min": 0.3556752820006188,
+            "max": 1.2477448099676303,
+            "count": 200
         },
         "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 8.082097306000007e-06,
-            "min": 8.082097306000007e-06,
-            "max": 0.000291882002706,
-            "count": 20
+            "value": 7.032997656000038e-07,
+            "min": 7.032997656000038e-07,
+            "max": 0.00029918820027059994,
+            "count": 200
         },
         "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 3.232838922400003e-05,
-            "min": 3.232838922400003e-05,
-            "max": 0.0013851600382800001,
-            "count": 20
+            "value": 3.516498828000019e-06,
+            "min": 3.516498828000019e-06,
+            "max": 0.001488516003828,
+            "count": 200
         },
         "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10269400000000001,
-            "min": 0.10269400000000001,
-            "max": 0.197294,
-            "count": 20
+            "value": 0.10023440000000002,
+            "min": 0.10023440000000002,
+            "max": 0.1997294,
+            "count": 200
         },
         "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.41077600000000003,
-            "min": 0.41077600000000003,
-            "max": 0.9617200000000001,
-            "count": 20
+            "value": 0.5011720000000001,
+            "min": 0.4029176,
+            "max": 0.9961720000000001,
+            "count": 200
         },
         "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.0001444306000000001,
-            "min": 0.0001444306000000001,
-            "max": 0.004864970599999999,
-            "count": 20
+            "value": 2.1696560000000063e-05,
+            "min": 2.1696560000000063e-05,
+            "max": 0.00498649706,
+            "count": 200
         },
         "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.0005777224000000004,
-            "min": 0.0005777224000000004,
-            "max": 0.023089828000000003,
-            "count": 20
+            "value": 0.00010848280000000032,
+            "min": 0.00010848280000000032,
+            "max": 0.024808982800000004,
+            "count": 200
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 26.636363636363637,
-            "min": 3.727272727272727,
-            "max": 26.672727272727272,
-            "count": 20
+            "value": 29.454545454545453,
+            "min": 3.7045454545454546,
+            "max": 29.75,
+            "count": 200
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1172.0,
-            "min": 164.0,
-            "max": 1467.0,
-            "count": 20
+            "value": 1620.0,
+            "min": 163.0,
+            "max": 1629.0,
+            "count": 200
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 26.636363636363637,
-            "min": 3.727272727272727,
-            "max": 26.672727272727272,
-            "count": 20
+            "value": 29.454545454545453,
+            "min": 3.7045454545454546,
+            "max": 29.75,
+            "count": 200
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1172.0,
-            "min": 164.0,
-            "max": 1467.0,
-            "count": 20
+            "value": 1620.0,
+            "min": 163.0,
+            "max": 1629.0,
+            "count": 200
         },
         "SnowballTarget.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 200
         },
         "SnowballTarget.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 200
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1673518265",
+        "start_time_seconds": "1673520245",
         "python_version": "3.8.16 (default, Dec  7 2022, 01:12:13) \n[GCC 7.5.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
         "mlagents_version": "0.29.0.dev0",
         "mlagents_envs_version": "0.29.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.8.1+cu102",
         "numpy_version": "1.21.6",
-        "end_time_seconds": "1673518721"
+        "end_time_seconds": "1673526354"
     },
-    "total": 455.72525350700005,
+    "total": 6108.450217839001,
     "count": 1,
-    "self": 0.3857958560001862,
+    "self": 0.38215958300133934,
     "children": {
         "run_training.setup": {
-            "total": 0.10357362599995668,
+            "total": 0.10299456399980045,
             "count": 1,
-            "self": 0.10357362599995668
+            "self": 0.10299456399980045
         },
         "TrainerController.start_learning": {
-            "total": 455.2358840249999,
+            "total": 6107.965063692,
             "count": 1,
-            "self": 0.46556983300706634,
+            "self": 4.670113652085092,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 6.5569539540000505,
+                    "total": 5.953856518000066,
                     "count": 1,
-                    "self": 6.5569539540000505
+                    "self": 5.953856518000066
                 },
                 "TrainerController.advance": {
-                    "total": 448.0569255599927,
-                    "count": 18207,
-                    "self": 0.25826927997013627,
+                    "total": 6097.172750531914,
+                    "count": 181879,
+                    "self": 2.3390944627126373,
                     "children": {
                         "env_step": {
-                            "total": 447.79865628002256,
-                            "count": 18207,
-                            "self": 289.74537027405825,
+                            "total": 6094.833656069201,
+                            "count": 181879,
+                            "self": 4547.217765226418,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 157.80370983698845,
-                                    "count": 18207,
-                                    "self": 1.4180494659875649,
+                                    "total": 1545.1520703661208,
+                                    "count": 181879,
+                                    "self": 13.06588448885941,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 156.38566037100088,
-                                            "count": 18207,
-                                            "self": 30.18173106801612,
+                                            "total": 1532.0861858772614,
+                                            "count": 181879,
+                                            "self": 303.9904630213814,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 126.20392930298476,
-                                                    "count": 18207,
-                                                    "self": 126.20392930298476
+                                                    "total": 1228.09572285588,
+                                                    "count": 181879,
+                                                    "self": 1228.09572285588
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.24957616897586377,
-                                    "count": 18207,
+                                    "total": 2.4638204766624767,
+                                    "count": 181879,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 454.0765676149855,
-                                            "count": 18207,
+                                            "total": 6097.303847972106,
+                                            "count": 181879,
                                             "is_parallel": true,
-                                            "self": 249.94183759298608,
+                                            "self": 4068.3793781252202,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -224,48 +224,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.005496245000017552,
+                                                            "total": 0.0018383219999122957,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0033799339998950018,
+                                                            "self": 0.0006221360004019516,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0021163110001225505,
+                                                                    "total": 0.0012161859995103441,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0021163110001225505
+                                                                    "self": 0.0012161859995103441
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.040358097000080306,
+                                                            "total": 0.03766531800010853,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0003301740000551945,
+                                                            "self": 0.00045596099971589865,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.000266355000007934,
+                                                                    "total": 0.00027069700036008726,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.000266355000007934
+                                                                    "self": 0.00027069700036008726
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.03796502199998031,
+                                                                    "total": 0.035113329000068916,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.03796502199998031
+                                                                    "self": 0.035113329000068916
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0017965460000368694,
+                                                                    "total": 0.0018253309999636258,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004052889999002218,
+                                                                    "self": 0.0004180810001344071,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0013912570001366475,
+                                                                            "total": 0.0014072499998292187,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0013912570001366475
+                                                                            "self": 0.0014072499998292187
                                                                         }
                                                                     }
                                                                 }
@@ -274,34 +274,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 204.13473002199942,
-                                                    "count": 18206,
+                                                    "total": 2028.924469846886,
+                                                    "count": 181878,
                                                     "is_parallel": true,
-                                                    "self": 8.044017081038646,
+                                                    "self": 80.32223734537229,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 4.7745306490077155,
-                                                            "count": 18206,
+                                                            "total": 48.73312923412368,
+                                                            "count": 181878,
                                                             "is_parallel": true,
-                                                            "self": 4.7745306490077155
+                                                            "self": 48.73312923412368
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 159.9456216239828,
-                                                            "count": 18206,
+                                                            "total": 1584.0304515685566,
+                                                            "count": 181878,
                                                             "is_parallel": true,
-                                                            "self": 159.9456216239828
+                                                            "self": 1584.0304515685566
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 31.370560667970267,
-                                                            "count": 18206,
+                                                            "total": 315.8386516988335,
+                                                            "count": 181878,
                                                             "is_parallel": true,
-                                                            "self": 6.266190823978718,
+                                                            "self": 62.35403560249006,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 25.10436984399155,
-                                                                    "count": 182060,
+                                                                    "total": 253.48461609634342,
+                                                                    "count": 1818780,
                                                                     "is_parallel": true,
-                                                                    "self": 25.10436984399155
+                                                                    "self": 253.48461609634342
                                                                 }
                                                             }
                                                         }
@@ -316,9 +316,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 4.6749999910389306e-05,
+                    "total": 4.2252999264746904e-05,
                     "count": 1,
-                    "self": 4.6749999910389306e-05,
+                    "self": 4.2252999264746904e-05,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -327,36 +327,36 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 445.58481400098435,
-                                    "count": 301694,
+                                    "total": 6073.711755697596,
+                                    "count": 2898609,
                                     "is_parallel": true,
-                                    "self": 7.394922741995629,
+                                    "self": 71.1986653173426,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 251.43741437098925,
-                                            "count": 301694,
+                                            "total": 2506.8915254542585,
+                                            "count": 2898609,
                                             "is_parallel": true,
-                                            "self": 250.51763818398945,
+                                            "self": 2496.2475137062534,
                                             "children": {
                                                 "RLTrainer._checkpoint": {
-                                                    "total": 0.9197761869997976,
-                                                    "count": 4,
+                                                    "total": 10.644011748005141,
+                                                    "count": 40,
                                                     "is_parallel": true,
-                                                    "self": 0.9197761869997976
+                                                    "self": 10.644011748005141
                                                 }
                                             }
                                         },
                                         "_update_policy": {
-                                            "total": 186.75247688799948,
-                                            "count": 90,
+                                            "total": 3495.6215649259952,
+                                            "count": 909,
                                             "is_parallel": true,
-                                            "self": 58.73896090899734,
+                                            "self": 1329.040408200864,
                                             "children": {
                                                 "TorchPPOOptimizer.update": {
-                                                    "total": 128.01351597900214,
-                                                    "count": 6116,
+                                                    "total": 2166.581156725131,
+                                                    "count": 154480,
                                                     "is_parallel": true,
-                                                    "self": 128.01351597900214
+                                                    "self": 2166.581156725131
                                                 }
                                             }
                                         }
@@ -367,14 +367,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.15638792800018564,
+                    "total": 0.16830073700111825,
                     "count": 1,
-                    "self": 0.0007655690003502968,
+                    "self": 0.0011941270022362005,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.15562235899983534,
+                            "total": 0.16710660999888205,
                             "count": 1,
-                            "self": 0.15562235899983534
+                            "self": 0.16710660999888205
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,58 +2,103 @@
     "SnowballTarget": {
         "checkpoints": [
             {
-                "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 18.0,
-                "creation_time": 1673518384.8692229,
+                "steps": 1599976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1599976.onnx",
+                "reward": 28.727272727272727,
+                "creation_time": 1673525132.381246,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1599976.pt"
                 ]
             },
             {
-                "steps": 99960,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 23.181818181818183,
-                "creation_time": 1673518497.0284586,
+                "steps": 1649992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1649992.onnx",
+                "reward": 28.8,
+                "creation_time": 1673525287.5226471,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1649992.pt"
                 ]
             },
             {
-                "steps": 149984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 25.636363636363637,
-                "creation_time": 1673518610.0635867,
+                "steps": 1699936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1699936.onnx",
+                "reward": 28.727272727272727,
+                "creation_time": 1673525437.6237686,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1699936.pt"
                 ]
             },
             {
-                "steps": 199984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 26.636363636363637,
-                "creation_time": 1673518721.0539124,
+                "steps": 1749960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1749960.onnx",
+                "reward": 29.727272727272727,
+                "creation_time": 1673525591.3778605,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1749960.pt"
                 ]
             },
             {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 26.636363636363637,
-                "creation_time": 1673518721.245005,
+                "steps": 1799984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1799984.onnx",
+                "reward": 28.09090909090909,
+                "creation_time": 1673525744.1430173,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1799984.pt"
+                ]
+            },
+            {
+                "steps": 1849984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1849984.onnx",
+                "reward": 29.818181818181817,
+                "creation_time": 1673525894.5144174,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1849984.pt"
+                ]
+            },
+            {
+                "steps": 1899944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1899944.onnx",
+                "reward": 30.272727272727273,
+                "creation_time": 1673526046.8500984,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1899944.pt"
+                ]
+            },
+            {
+                "steps": 1949968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1949968.onnx",
+                "reward": 29.818181818181817,
+                "creation_time": 1673526199.7416418,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1949968.pt"
+                ]
+            },
+            {
+                "steps": 1999992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1999992.onnx",
+                "reward": 29.636363636363637,
+                "creation_time": 1673526353.5031881,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1999992.pt"
+                ]
+            },
+            {
+                "steps": 2000376,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-2000376.onnx",
+                "reward": 29.636363636363637,
+                "creation_time": 1673526353.7504578,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-2000376.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 200112,
+            "steps": 2000376,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 26.636363636363637,
-            "creation_time": 1673518721.245005,
+            "reward": 29.636363636363637,
+            "creation_time": 1673526353.7504578,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-2000376.pt"
             ]
         }
     },