First Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47ae9f5cb552438ff301578741cff6947f4d1955f9a87e565cf6ce2d98d79e14
+oid sha256:e92a64060439f4f5deca065f17a8ede631f18f8c4a90a89de83a16b8841c54a3
 size 645119

SnowballTarget/SnowballTarget-149960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33128be452732bef17892622c1df086cbbaa6d3f60fcb0f190938e7bbc28cde1
+size 645119

SnowballTarget/SnowballTarget-149960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d32a0dfd1bd07fa65a9f5875ceff7986284ca65d4051f74cd744b0300b123d2
+size 3845299

SnowballTarget/SnowballTarget-199960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e92a64060439f4f5deca065f17a8ede631f18f8c4a90a89de83a16b8841c54a3
+size 645119

SnowballTarget/SnowballTarget-199960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f49d1234839aa0c9218ea0c65884c11eec2dfdb3982a816ca09216d0f51e14a7
+size 3845299

SnowballTarget/SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e92a64060439f4f5deca065f17a8ede631f18f8c4a90a89de83a16b8841c54a3
+size 645119

SnowballTarget/SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a527e782326eb5e1b48152b2c4f82f4d858a19cfb641ebbb2e3023db4a63664f
+size 3845299

SnowballTarget/SnowballTarget-49976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d33d2b642d64561dcf6666781ed9252af8d5f71504cbf0cc5c390a2d2a62b69
+size 645119

SnowballTarget/SnowballTarget-49976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a061d0239e470cc7802f3bedf505c3ab52a9f4987b292af5f69eab0b9fdac03d
+size 3845299

SnowballTarget/SnowballTarget-99936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe09bc6cabce92dedbca5ffcba22451748714c623c74fa1636a28f9c5ce28ad4
+size 645119

SnowballTarget/SnowballTarget-99936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:099eb1ea6a91d78be51084b647d50de0914c01b62c964c084e50f3977fba3da6
+size 3845299

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d546383522b8b6cb8e090b491e3fee6f708ca2b90a877e06835a08cefbd634a8
-size 3845591
+oid sha256:a527e782326eb5e1b48152b2c4f82f4d858a19cfb641ebbb2e3023db4a63664f
+size 3845299

SnowballTarget/events.out.tfevents.1676357818.764a44ba2aac.4216.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cc7e82abbe855eb60a7dc7bf88b2599f0f572b2f7814f8be43c6e73b457e78d
+size 23539

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, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "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": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "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": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -65,7 +65,7 @@ checkpoint_settings:
   run_id: SnowballTarget1
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: false

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:2642:(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  0.085 seconds
+- Completed reload, in  0.089 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: 0.772108 ms
+UnloadTime: 0.896819 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]: 186 frames, [16.0 KB-32.0 KB]: 3 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 5192 frames, [16.0 KB-32.0 KB]: 88 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 29
+  Peak main deferred allocation count 45
     [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]: 190 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 5281 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.1 MB
+      Peak Allocated memory 6.7 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 190 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 5281 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.9 MB
+      Peak Allocated memory 17.8 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 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 165 frames, [64.0 KB-128.0 KB]: 25 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 3587 frames, [64.0 KB-128.0 KB]: 1694 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 65.6 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]: 190 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5281 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 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 190 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5281 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]: 189 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5280 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 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 190 frames
+      Peak usage frame count: [0-1.0 KB]: 5281 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]: 190 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 5281 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -1,75 +1,221 @@
 {
     "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 1.1544607877731323,
+            "min": 1.1418404579162598,
+            "max": 2.8374648094177246,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 11022.7919921875,
+            "min": 10487.26953125,
+            "max": 28358.654296875,
+            "count": 20
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 199960.0,
+            "min": 9992.0,
+            "max": 199960.0,
+            "count": 20
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 199960.0,
+            "min": 9992.0,
+            "max": 199960.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 12.51748275756836,
+            "min": 0.5854502320289612,
+            "max": 12.51748275756836,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2440.9091796875,
+            "min": 37.468814849853516,
+            "max": 2501.917724609375,
+            "count": 20
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 20
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 8756.0,
+            "min": 2189.0,
+            "max": 10945.0,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.07200062442394019,
+            "min": 0.06332857517723003,
+            "max": 0.07463651072248467,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.28800249769576075,
+            "min": 0.07463651072248467,
+            "max": 0.3631651440073791,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.20859267577236773,
+            "min": 0.12093222917368014,
+            "max": 0.2943200986759335,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.8343707030894709,
+            "min": 0.12093222917368014,
+            "max": 1.4716004933796676,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 8.214097262000005e-06,
+            "min": 8.214097262000005e-06,
+            "max": 0.000287064004312,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 3.285638904800002e-05,
+            "min": 3.285638904800002e-05,
+            "max": 0.0013858200380599999,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10273800000000001,
+            "min": 0.10273800000000001,
+            "max": 0.195688,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.41095200000000004,
+            "min": 0.195688,
+            "max": 0.96194,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.0001466262000000001,
+            "min": 0.0001466262000000001,
+            "max": 0.0047848312,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0005865048000000004,
+            "min": 0.0005865048000000004,
+            "max": 0.023100806,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 25.181818181818183,
+            "min": 3.0,
+            "max": 25.181818181818183,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1108.0,
+            "min": 33.0,
+            "max": 1356.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 25.181818181818183,
+            "min": 3.0,
+            "max": 25.181818181818183,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1108.0,
+            "min": 33.0,
+            "max": 1356.0,
+            "count": 20
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 20
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 20
+        }
+    },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1676357680",
+        "start_time_seconds": "1676357815",
         "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
         "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": "1676357704"
+        "end_time_seconds": "1676358244"
     },
-    "total": 23.961669594,
+    "total": 429.195851535,
     "count": 1,
-    "self": 0.0161653220000062,
+    "self": 0.7867629780000698,
     "children": {
         "run_training.setup": {
-            "total": 0.10727534900001956,
+            "total": 0.10947037599999021,
             "count": 1,
-            "self": 0.10727534900001956
+            "self": 0.10947037599999021
         },
         "TrainerController.start_learning": {
-            "total": 23.838228922999974,
+            "total": 428.2996181809999,
             "count": 1,
-            "self": 0.6965058030009459,
+            "self": 0.4835444070047288,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 9.167666871999927,
+                    "total": 7.101543563000064,
                     "count": 1,
-                    "self": 9.167666871999927
+                    "self": 7.101543563000064
                 },
                 "TrainerController.advance": {
-                    "total": 13.768805741999017,
-                    "count": 632,
-                    "self": 0.008519770000589233,
+                    "total": 420.54435335099504,
+                    "count": 17601,
+                    "self": 0.2362031210132045,
                     "children": {
                         "env_step": {
-                            "total": 13.760285971998428,
-                            "count": 632,
-                            "self": 9.291732637994755,
+                            "total": 420.30815022998183,
+                            "count": 17601,
+                            "self": 287.01985280700194,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 4.460123609000107,
-                                    "count": 632,
-                                    "self": 0.049056111998538654,
+                                    "total": 133.04257722399723,
+                                    "count": 17601,
+                                    "self": 1.337058558982335,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 4.411067497001568,
-                                            "count": 632,
-                                            "self": 0.8989476640019802,
+                                            "total": 131.7055186650149,
+                                            "count": 17601,
+                                            "self": 28.767387893044088,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 3.5121198329995877,
-                                                    "count": 632,
-                                                    "self": 3.5121198329995877
+                                                    "total": 102.9381307719708,
+                                                    "count": 17601,
+                                                    "self": 102.9381307719708
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.008429725003566091,
-                                    "count": 631,
+                                    "total": 0.24572019898266717,
+                                    "count": 17601,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 22.959840870997482,
-                                            "count": 631,
+                                            "total": 426.8952240950083,
+                                            "count": 17601,
                                             "is_parallel": true,
-                                            "self": 15.546209170997713,
+                                            "self": 204.91237196101076,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -78,48 +224,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.006464282000024468,
+                                                            "total": 0.002771187000007558,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.003847750999852906,
+                                                            "self": 0.0009383529999240636,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0026165310001715625,
+                                                                    "total": 0.0018328340000834942,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0026165310001715625
+                                                                    "self": 0.0018328340000834942
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.03272560599998542,
+                                                            "total": 0.048828276999984155,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005299789999071436,
+                                                            "self": 0.00035553700013224443,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0003979750000553395,
+                                                                    "total": 0.000303159999930358,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003979750000553395
+                                                                    "self": 0.000303159999930358
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.029979563999972925,
+                                                                    "total": 0.046980107999957,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.029979563999972925
+                                                                    "self": 0.046980107999957
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.001818088000050011,
+                                                                    "total": 0.001189471999964553,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00042160399971180595,
+                                                                    "self": 0.00031896499990580196,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001396484000338205,
+                                                                            "total": 0.0008705070000587511,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001396484000338205
+                                                                            "self": 0.0008705070000587511
                                                                         }
                                                                     }
                                                                 }
@@ -128,34 +274,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 7.413631699999769,
-                                                    "count": 630,
+                                                    "total": 221.98285213399754,
+                                                    "count": 17600,
                                                     "is_parallel": true,
-                                                    "self": 0.3222497699999849,
+                                                    "self": 8.80142734503238,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 0.17315156899928752,
-                                                            "count": 630,
+                                                            "total": 4.804668293981649,
+                                                            "count": 17600,
                                                             "is_parallel": true,
-                                                            "self": 0.17315156899928752
+                                                            "self": 4.804668293981649
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 5.880807032999996,
-                                                            "count": 630,
+                                                            "total": 177.39940563599407,
+                                                            "count": 17600,
                                                             "is_parallel": true,
-                                                            "self": 5.880807032999996
+                                                            "self": 177.39940563599407
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 1.0374233280005,
-                                                            "count": 630,
+                                                            "total": 30.97735085898944,
+                                                            "count": 17600,
                                                             "is_parallel": true,
-                                                            "self": 0.22832736900852524,
+                                                            "self": 6.243455937015938,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.8090959589919748,
-                                                                    "count": 6300,
+                                                                    "total": 24.7338949219735,
+                                                                    "count": 176000,
                                                                     "is_parallel": true,
-                                                                    "self": 0.8090959589919748
+                                                                    "self": 24.7338949219735
                                                                 }
                                                             }
                                                         }
@@ -170,9 +316,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 3.7505000022974855e-05,
+                    "total": 0.00010480700007065025,
                     "count": 1,
-                    "self": 3.7505000022974855e-05,
+                    "self": 0.00010480700007065025,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -181,28 +327,36 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 14.3192820480092,
-                                    "count": 16188,
+                                    "total": 417.3458928389284,
+                                    "count": 376609,
                                     "is_parallel": true,
-                                    "self": 0.35730666300935354,
+                                    "self": 9.302657343984947,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 8.980585511999834,
-                                            "count": 16188,
+                                            "total": 241.24910940894392,
+                                            "count": 376609,
                                             "is_parallel": true,
-                                            "self": 8.980585511999834
+                                            "self": 239.79841103594413,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 1.4506983729997955,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 1.4506983729997955
+                                                }
+                                            }
                                         },
                                         "_update_policy": {
-                                            "total": 4.981389873000012,
-                                            "count": 3,
+                                            "total": 166.79412608599955,
+                                            "count": 87,
                                             "is_parallel": true,
-                                            "self": 1.596088421000104,
+                                            "self": 55.87059514500356,
                                             "children": {
                                                 "TorchPPOOptimizer.update": {
-                                                    "total": 3.385301451999908,
-                                                    "count": 150,
+                                                    "total": 110.92353094099599,
+                                                    "count": 4434,
                                                     "is_parallel": true,
-                                                    "self": 3.385301451999908
+                                                    "self": 110.92353094099599
                                                 }
                                             }
                                         }
@@ -213,14 +367,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.205213001000061,
+                    "total": 0.1700720530000126,
                     "count": 1,
-                    "self": 0.0010941920000959726,
+                    "self": 0.002315073000090706,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.20411880899996504,
+                            "total": 0.1677569799999219,
                             "count": 1,
-                            "self": 0.20411880899996504
+                            "self": 0.1677569799999219
                         }
                     }
                 }

run_logs/training_status.json

@@ -9,15 +9,60 @@
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-6512.pt"
                 ]
+            },
+            {
+                "steps": 49976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49976.onnx",
+                "reward": 13.0,
+                "creation_time": 1676357918.0925944,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49976.pt"
+                ]
+            },
+            {
+                "steps": 99936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99936.onnx",
+                "reward": 18.90909090909091,
+                "creation_time": 1676358026.1965964,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99936.pt"
+                ]
+            },
+            {
+                "steps": 149960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149960.onnx",
+                "reward": 22.0,
+                "creation_time": 1676358135.8192575,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149960.pt"
+                ]
+            },
+            {
+                "steps": 199960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199960.onnx",
+                "reward": 24.636363636363637,
+                "creation_time": 1676358243.3238916,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199960.pt"
+                ]
+            },
+            {
+                "steps": 200112,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 24.681818181818183,
+                "creation_time": 1676358243.536194,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 6512,
+            "steps": 200112,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": null,
-            "creation_time": 1676357704.5574577,
+            "reward": 24.681818181818183,
+            "creation_time": 1676358243.536194,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-6512.pt"
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
             ]
         }
     },