First Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:947640b7468c36b815208154df6fa5329e423e21f038e442e44601a664a12b01
+oid sha256:da782e7485f848025f322c5f2aeaad9f8dfbb037bd2096fe61d0b9300bb0fdea
 size 650646

SnowballTarget/SnowballTarget-1000208.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da782e7485f848025f322c5f2aeaad9f8dfbb037bd2096fe61d0b9300bb0fdea
+size 650646

SnowballTarget/SnowballTarget-1000208.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:796c5d45c0c4a91bfc8acb0d9b2c58e43ab6d69924c280d18d1d44b3a31a80ec
+size 3850214

SnowballTarget/SnowballTarget-599936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54c066e73216feeca990400fb2d02025e13f01c604c01c99fff13a329239a323
+size 650646

SnowballTarget/SnowballTarget-599936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bb0c55637b3a66fc9eeb04917968b8e90308ee719fc21b4c7664830ebfd4d9d
+size 3850075

SnowballTarget/SnowballTarget-649960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b58929c1f3157825c443a3613597f908ac047bfd78c2a1280a3718bffd545067
+size 650646

SnowballTarget/SnowballTarget-649960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e55a8ee71346a9ed2700b8d8539419b89228b2f69e4e1eb800cbe52e15b41cfb
+size 3850075

SnowballTarget/SnowballTarget-699984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0630d16a6d03e04388ccc3e3bc91f90bfa74436b7b494f852671b7772e71e36c
+size 650646

SnowballTarget/SnowballTarget-699984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddcb0190cbc1ee35520d6ec5a55a644e6512e30fae15032afa64974d6bb0d490
+size 3850075

SnowballTarget/SnowballTarget-749984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2d532355daf0dd4279b70389f686bffa8afe1c3675b5129c6d57c31bf157082
+size 650646

SnowballTarget/SnowballTarget-749984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79533a737a01e9aec3130995bb8d787693813fb4ea2811660eb029829e6d75b3
+size 3850075

SnowballTarget/SnowballTarget-799944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f65bd4ab2639e8670a2fc735f78eb372a7ae042dfed6c4d0badf5dd419c151c
+size 650646

SnowballTarget/SnowballTarget-799944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30646384f8911cba2c736b47dc877960bc2ffb80de049d698ae58e91719cce68
+size 3850075

SnowballTarget/SnowballTarget-849968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac7223dfdd3b8778b526d1214a5159325d751117cbf813ed390fe03fec37931d
+size 650646

SnowballTarget/SnowballTarget-849968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08c1f566a96ff4e1c6df95c042b6a26ac7a79034c4802e9c40a8a2d87e75b5b0
+size 3850075

SnowballTarget/SnowballTarget-899992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f5163c8c59d814370b1be75031f0e9c179f8249647ab2a64c2bddc3273b8cd1
+size 650646

SnowballTarget/SnowballTarget-899992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e02ca6dc8e6b03078ab70924c9e399d02f155a6c248ba6fef34a71f8c9dbbb3
+size 3850075

SnowballTarget/SnowballTarget-949992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55f648b1650c60b95db232a7ddda42851cdd1f56bf4fb69c10c5018cd59a410b
+size 650646

SnowballTarget/SnowballTarget-949992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:806e24fea1d199cf75c344c9bb2b66dccf7c0445ef852afcfdb666563a0fdbf9
+size 3850075

SnowballTarget/SnowballTarget-999952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da782e7485f848025f322c5f2aeaad9f8dfbb037bd2096fe61d0b9300bb0fdea
+size 650646

SnowballTarget/SnowballTarget-999952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25e3bfd462b0b68b5e3e5341f363415d05822169fca11503c3ba7e40227b5838
+size 3850075

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6f820586e165a71be6d95f588ae225b78a606e16ca629f1eb494936d7491146
+oid sha256:d05c8a32856bbd8dd116726df59e974bdc630974fe86f5a38bbf4f1c6ecad95b
 size 3849250

SnowballTarget/events.out.tfevents.1704282375.01799f74e6db.3468.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86994001e276e2498d13c77d904d733779d4fe8fbc2dc3558d443b452a4588ad
+size 99511

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": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "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, "even_checkpoints": false, "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, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "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": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "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, "even_checkpoints": false, "max_steps": 1000000, "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, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "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}

configuration.yaml

@@ -38,7 +38,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 10
     even_checkpoints: false
-    max_steps: 200000
+    max_steps: 1000000
     time_horizon: 64
     summary_freq: 10000
     threaded: true

run_logs/Player-0.log

@@ -34,7 +34,7 @@ ALSA lib pcm.c:2664:(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  0.125 seconds
+- Completed reload, in  0.093 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 +45,7 @@ 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: 0.866556 ms
+UnloadTime: 0.932543 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 +53,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 5368 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]: 26826 frames, [16.0 KB-32.0 KB]: 454 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
@@ -169,19 +169,19 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 40
+  Peak main deferred allocation count 42
     [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]: 5460 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 11345 frames, [8.0 MB-16.0 MB]: 15936 frames
       Requested Block Size 16.0 MB
-      Peak Block count 1
-      Peak Allocated memory 6.7 MB
+      Peak Block count 2
+      Peak Allocated memory 14.5 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 5460 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 27281 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 17.8 MB
@@ -213,13 +213,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 4748 frames, [64.0 KB-128.0 KB]: 712 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 26297 frames, [64.0 KB-128.0 KB]: 984 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 66.8 KB
+      Peak Allocated memory 66.4 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 5460 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 27281 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -231,13 +231,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 5460 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 27281 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]: 5459 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 27280 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 +249,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 5460 frames
+      Peak usage frame count: [0-1.0 KB]: 27281 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]: 5460 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 27281 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -2,153 +2,153 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 0.8926981687545776,
-            "min": 0.8926981687545776,
-            "max": 2.864619016647339,
-            "count": 20
+            "value": 0.6556198000907898,
+            "min": 0.6556198000907898,
+            "max": 2.8616464138031006,
+            "count": 100
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 8533.3017578125,
-            "min": 8533.3017578125,
-            "max": 29399.5859375,
-            "count": 20
+            "value": 6238.22265625,
+            "min": 6238.22265625,
+            "max": 29306.12109375,
+            "count": 100
         },
         "SnowballTarget.Step.mean": {
-            "value": 199984.0,
+            "value": 999952.0,
             "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+            "max": 999952.0,
+            "count": 100
         },
         "SnowballTarget.Step.sum": {
-            "value": 199984.0,
+            "value": 999952.0,
             "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+            "max": 999952.0,
+            "count": 100
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 12.87562370300293,
-            "min": 0.25858643651008606,
-            "max": 12.87562370300293,
-            "count": 20
+            "value": 13.972919464111328,
+            "min": 0.29344210028648376,
+            "max": 14.223943710327148,
+            "count": 100
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2510.74658203125,
-            "min": 50.165767669677734,
-            "max": 2624.95263671875,
-            "count": 20
+            "value": 2724.71923828125,
+            "min": 56.927764892578125,
+            "max": 2915.908447265625,
+            "count": 100
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
             "value": 199.0,
             "min": 199.0,
             "max": 199.0,
-            "count": 20
+            "count": 100
         },
         "SnowballTarget.Environment.EpisodeLength.sum": {
             "value": 8756.0,
             "min": 8756.0,
             "max": 10945.0,
-            "count": 20
+            "count": 100
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.06661319639619358,
-            "min": 0.059019445786540094,
-            "max": 0.07523157740719148,
-            "count": 20
+            "value": 0.06891079435830333,
+            "min": 0.06007124235172038,
+            "max": 0.07707131814494657,
+            "count": 100
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.2664527855847743,
-            "min": 0.23607778314616037,
-            "max": 0.36230462937451463,
-            "count": 20
+            "value": 0.2756431774332133,
+            "min": 0.24028496940688152,
+            "max": 0.38535659072473283,
+            "count": 100
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.1943440443890936,
-            "min": 0.10913778841495514,
-            "max": 0.28274346169303444,
-            "count": 20
+            "value": 0.14685648712603483,
+            "min": 0.11214490902299683,
+            "max": 0.28962309563568994,
+            "count": 100
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.7773761775563744,
-            "min": 0.43655115365982056,
-            "max": 1.4137173084651722,
-            "count": 20
+            "value": 0.5874259485041393,
+            "min": 0.4485796360919873,
+            "max": 1.327513700898956,
+            "count": 100
         },
         "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 8.082097306000005e-06,
-            "min": 8.082097306000005e-06,
-            "max": 0.000291882002706,
-            "count": 20
+            "value": 1.3764995412000027e-06,
+            "min": 1.3764995412000027e-06,
+            "max": 0.0002983764005411999,
+            "count": 100
         },
         "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 3.232838922400002e-05,
-            "min": 3.232838922400002e-05,
-            "max": 0.00138516003828,
-            "count": 20
+            "value": 5.505998164800011e-06,
+            "min": 5.505998164800011e-06,
+            "max": 0.001477032007656,
+            "count": 100
         },
         "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10269400000000001,
-            "min": 0.10269400000000001,
-            "max": 0.19729400000000002,
-            "count": 20
+            "value": 0.10045880000000001,
+            "min": 0.10045880000000001,
+            "max": 0.1994588,
+            "count": 100
         },
         "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.41077600000000003,
-            "min": 0.41077600000000003,
-            "max": 0.96172,
-            "count": 20
+            "value": 0.40183520000000006,
+            "min": 0.40183520000000006,
+            "max": 0.992344,
+            "count": 100
         },
         "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.0001444306000000001,
-            "min": 0.0001444306000000001,
-            "max": 0.0048649706,
-            "count": 20
+            "value": 3.289412000000004e-05,
+            "min": 3.289412000000004e-05,
+            "max": 0.00497299412,
+            "count": 100
         },
         "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.0005777224000000004,
-            "min": 0.0005777224000000004,
-            "max": 0.023089828,
-            "count": 20
+            "value": 0.00013157648000000017,
+            "min": 0.00013157648000000017,
+            "max": 0.0246179656,
+            "count": 100
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 25.136363636363637,
-            "min": 3.227272727272727,
-            "max": 26.0,
-            "count": 20
+            "value": 27.444444444444443,
+            "min": 3.0454545454545454,
+            "max": 28.227272727272727,
+            "count": 100
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1106.0,
-            "min": 142.0,
-            "max": 1397.0,
-            "count": 20
+            "value": 1235.0,
+            "min": 134.0,
+            "max": 1538.0,
+            "count": 100
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 25.136363636363637,
-            "min": 3.227272727272727,
-            "max": 26.0,
-            "count": 20
+            "value": 27.444444444444443,
+            "min": 3.0454545454545454,
+            "max": 28.227272727272727,
+            "count": 100
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1106.0,
-            "min": 142.0,
-            "max": 1397.0,
-            "count": 20
+            "value": 1235.0,
+            "min": 134.0,
+            "max": 1538.0,
+            "count": 100
         },
         "SnowballTarget.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 100
         },
         "SnowballTarget.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 100
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1704187906",
+        "start_time_seconds": "1704282374",
         "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
         "mlagents_version": "1.1.0.dev0",
@@ -156,59 +156,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.1.2+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1704188392"
+        "end_time_seconds": "1704284666"
     },
-    "total": 485.83262526900006,
+    "total": 2292.328304225,
     "count": 1,
-    "self": 0.443799375000026,
+    "self": 0.44431485899986,
     "children": {
         "run_training.setup": {
-            "total": 0.07352820400001292,
+            "total": 0.05248547400003645,
             "count": 1,
-            "self": 0.07352820400001292
+            "self": 0.05248547400003645
         },
         "TrainerController.start_learning": {
-            "total": 485.31529769,
+            "total": 2291.831503892,
             "count": 1,
-            "self": 0.6293133820054209,
+            "self": 2.8727537150116405,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.4484712180000088,
+                    "total": 3.2193444739999677,
                     "count": 1,
-                    "self": 3.4484712180000088
+                    "self": 3.2193444739999677
                 },
                 "TrainerController.advance": {
-                    "total": 481.1435667619946,
-                    "count": 18199,
-                    "self": 0.3062812119932232,
+                    "total": 2285.644657805988,
+                    "count": 90935,
+                    "self": 1.489981793959032,
                     "children": {
                         "env_step": {
-                            "total": 480.83728555000135,
-                            "count": 18199,
-                            "self": 317.71809394198783,
+                            "total": 2284.154676012029,
+                            "count": 90935,
+                            "self": 1498.9616912490487,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 162.80571340400735,
-                                    "count": 18199,
-                                    "self": 1.615548247009599,
+                                    "total": 783.7169014840048,
+                                    "count": 90935,
+                                    "self": 7.491208335028773,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 161.19016515699775,
-                                            "count": 18199,
-                                            "self": 161.19016515699775
+                                            "total": 776.225693148976,
+                                            "count": 90935,
+                                            "self": 776.225693148976
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.31347820400617366,
-                                    "count": 18199,
+                                    "total": 1.4760832789756932,
+                                    "count": 90935,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 483.9407094110033,
-                                            "count": 18199,
+                                            "total": 2285.3747079809837,
+                                            "count": 90935,
                                             "is_parallel": true,
-                                            "self": 238.65188406900216,
+                                            "self": 1122.6868134669612,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.007749993999993876,
+                                                            "total": 0.0052974980000044525,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.004207652000047801,
+                                                            "self": 0.004004996999924515,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.003542341999946075,
+                                                                    "total": 0.0012925010000799375,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.003542341999946075
+                                                                    "self": 0.0012925010000799375
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04284389099996133,
+                                                            "total": 0.03913824200003546,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0007292310000366342,
+                                                            "self": 0.000681891999988693,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00046798699997907534,
+                                                                    "total": 0.00042681000002176006,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00046798699997907534
+                                                                    "self": 0.00042681000002176006
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.03941229499997689,
+                                                                    "total": 0.03592935500000749,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.03941229499997689
+                                                                    "self": 0.03592935500000749
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0022343779999687285,
+                                                                    "total": 0.002100185000017518,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00044628100005184024,
+                                                                    "self": 0.0004115399999591318,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0017880969999168883,
+                                                                            "total": 0.0016886450000583864,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0017880969999168883
+                                                                            "self": 0.0016886450000583864
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 245.28882534200113,
-                                                    "count": 18198,
+                                                    "total": 1162.6878945140224,
+                                                    "count": 90934,
                                                     "is_parallel": true,
-                                                    "self": 11.716177020005887,
+                                                    "self": 54.87933442413441,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 6.113793872999395,
-                                                            "count": 18198,
+                                                            "total": 27.785904660984556,
+                                                            "count": 90934,
                                                             "is_parallel": true,
-                                                            "self": 6.113793872999395
+                                                            "self": 27.785904660984556
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 189.42125516400927,
-                                                            "count": 18198,
+                                                            "total": 903.4905963699863,
+                                                            "count": 90934,
                                                             "is_parallel": true,
-                                                            "self": 189.42125516400927
+                                                            "self": 903.4905963699863
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 38.037599284986584,
-                                                            "count": 18198,
+                                                            "total": 176.53205905891718,
+                                                            "count": 90934,
                                                             "is_parallel": true,
-                                                            "self": 7.125858732973825,
+                                                            "self": 33.06144935106772,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 30.91174055201276,
-                                                                    "count": 181980,
+                                                                    "total": 143.47060970784946,
+                                                                    "count": 909340,
                                                                     "is_parallel": true,
-                                                                    "self": 30.91174055201276
+                                                                    "self": 143.47060970784946
                                                                 }
                                                             }
                                                         }
@@ -309,9 +309,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 0.00019253400000707188,
+                    "total": 0.00022406200014302158,
                     "count": 1,
-                    "self": 0.00019253400000707188,
+                    "self": 0.00022406200014302158,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -320,36 +320,36 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 474.90844625609213,
-                                    "count": 722370,
+                                    "total": 2256.9824222361353,
+                                    "count": 3470729,
                                     "is_parallel": true,
-                                    "self": 15.933353743103396,
+                                    "self": 73.82584219507453,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 264.1955855879884,
-                                            "count": 722370,
+                                            "total": 1243.1144788980619,
+                                            "count": 3470729,
                                             "is_parallel": true,
-                                            "self": 262.9897898169884,
+                                            "self": 1240.0073659410616,
                                             "children": {
                                                 "RLTrainer._checkpoint": {
-                                                    "total": 1.2057957709999982,
-                                                    "count": 4,
+                                                    "total": 3.107112957000254,
+                                                    "count": 20,
                                                     "is_parallel": true,
-                                                    "self": 1.2057957709999982
+                                                    "self": 3.107112957000254
                                                 }
                                             }
                                         },
                                         "_update_policy": {
-                                            "total": 194.77950692500036,
-                                            "count": 90,
+                                            "total": 940.0421011429992,
+                                            "count": 454,
                                             "is_parallel": true,
-                                            "self": 61.61043318499901,
+                                            "self": 294.46607319399584,
                                             "children": {
                                                 "TorchPPOOptimizer.update": {
-                                                    "total": 133.16907374000135,
-                                                    "count": 4587,
+                                                    "total": 645.5760279490033,
+                                                    "count": 23145,
                                                     "is_parallel": true,
-                                                    "self": 133.16907374000135
+                                                    "self": 645.5760279490033
                                                 }
                                             }
                                         }
@@ -360,14 +360,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.09375379400000838,
+                    "total": 0.09452383500001815,
                     "count": 1,
-                    "self": 0.0009610990000510355,
+                    "self": 0.001024473000143189,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.09279269499995735,
+                            "total": 0.09349936199987496,
                             "count": 1,
-                            "self": 0.09279269499995735
+                            "self": 0.09349936199987496
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,58 +2,103 @@
     "SnowballTarget": {
         "checkpoints": [
             {
-                "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 11.818181818181818,
-                "creation_time": 1704188030.7655182,
+                "steps": 599936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-599936.onnx",
+                "reward": 27.09090909090909,
+                "creation_time": 1704283754.154496,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-599936.pt"
                 ]
             },
             {
-                "steps": 99960,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 21.181818181818183,
-                "creation_time": 1704188152.1217024,
+                "steps": 649960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-649960.onnx",
+                "reward": 27.0,
+                "creation_time": 1704283866.6148787,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-649960.pt"
                 ]
             },
             {
-                "steps": 149984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 24.363636363636363,
-                "creation_time": 1704188272.6358979,
+                "steps": 699984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-699984.onnx",
+                "reward": 27.0,
+                "creation_time": 1704283980.1546278,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-699984.pt"
                 ]
             },
             {
-                "steps": 199984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 25.545454545454547,
-                "creation_time": 1704188391.9212785,
+                "steps": 749984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-749984.onnx",
+                "reward": 28.181818181818183,
+                "creation_time": 1704284093.6219976,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-749984.pt"
                 ]
             },
             {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 25.545454545454547,
-                "creation_time": 1704188392.0395799,
+                "steps": 799944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-799944.onnx",
+                "reward": 28.09090909090909,
+                "creation_time": 1704284206.0052483,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-799944.pt"
+                ]
+            },
+            {
+                "steps": 849968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-849968.onnx",
+                "reward": 27.272727272727273,
+                "creation_time": 1704284323.6923735,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-849968.pt"
+                ]
+            },
+            {
+                "steps": 899992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-899992.onnx",
+                "reward": 26.818181818181817,
+                "creation_time": 1704284439.8937619,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-899992.pt"
+                ]
+            },
+            {
+                "steps": 949992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-949992.onnx",
+                "reward": 27.09090909090909,
+                "creation_time": 1704284553.4172535,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-949992.pt"
+                ]
+            },
+            {
+                "steps": 999952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-999952.onnx",
+                "reward": 27.727272727272727,
+                "creation_time": 1704284666.0545616,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-999952.pt"
+                ]
+            },
+            {
+                "steps": 1000208,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000208.onnx",
+                "reward": 27.727272727272727,
+                "creation_time": 1704284666.1897485,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000208.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 200112,
+            "steps": 1000208,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 25.545454545454547,
-            "creation_time": 1704188392.0395799,
+            "reward": 27.727272727272727,
+            "creation_time": 1704284666.1897485,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-1000208.pt"
             ]
         }
     },