Second Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19e59d2e43a62fed3cd1421aa34915ee4e830524e4372a956e34927ee0499c7b
+oid sha256:a8be2ecdac0362dfab1fc6a9e4077e25565c7d38a1f93ace00f73c87eaaabb4f
 size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:880b2ee3cfb8d3ceef3104112387408547d868832caaecc3da861aa8411cb83d
+size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f08ba51219a457708f05dd9a70b9c2c219a2e0b5659eb4434551f8cfc245e83e
+size 3850075

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8be2ecdac0362dfab1fc6a9e4077e25565c7d38a1f93ace00f73c87eaaabb4f
+size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:070b6666a0770e8d1d9b5a1f3364b46837d9d218b0821b39410f9f20cbb31791
+size 3850075

SnowballTarget/SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8be2ecdac0362dfab1fc6a9e4077e25565c7d38a1f93ace00f73c87eaaabb4f
+size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06ba60b52eca5a34d8e1994115e0dbef5f55ea66c69cedc1c6ef129a85459a62
+size 3850075

SnowballTarget/SnowballTarget-49936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dcacae8ca4f7579524825f32b901258ec4429d385cb3f5db9f0b424a266f6f9
+size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e116512a425d3174f020635a8d170a2b9cc4d61753dcc1bfb3f637b6f71eb523
+size 3850000

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d63b7ea9189d9b734f659f3a3164eb9de720817e7d9868de756b087d0a54a15
+size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce6400af66e32217e04e9152f61265faa9a10089be3cacae957720d59215990
+size 3850000

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d77a5bee5ace6866d6e29e310641e408f24e3b1e5f30cf7701e300fe1b0bf7bc
+oid sha256:8a2bdae0573251471aa469aac655bc617a37dfe8030d5db09cbf0cfd68b608a7
 size 3849250

SnowballTarget/events.out.tfevents.1703604745.a0deab9a9f9d.13536.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42f5dd0874cb01ca8d398af21615ac78c0154380aa8c2d52d00be60118c1ece2
+size 24004

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": 5000, "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": 20000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": null, "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": true, "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": 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": "SnowballTarget2", "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

@@ -14,7 +14,7 @@ behaviors:
       learning_rate_schedule: linear
       beta_schedule: linear
       epsilon_schedule: linear
-    checkpoint_interval: 5000
+    checkpoint_interval: 50000
     network_settings:
       normalize: false
       hidden_units: 256
@@ -38,14 +38,14 @@ behaviors:
     init_path: null
     keep_checkpoints: 10
     even_checkpoints: false
-    max_steps: 20000
+    max_steps: 200000
     time_horizon: 64
     summary_freq: 10000
     threaded: true
     self_play: null
     behavioral_cloning: null
 env_settings:
-  env_path: null
+  env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
   env_args: null
   base_port: 5005
   num_envs: 1
@@ -66,10 +66,10 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: SnowballTarget1
+  run_id: SnowballTarget2
   initialize_from: null
   load_model: false
-  resume: true
+  resume: false
   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: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  0.086 seconds
+- Completed reload, in  0.124 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)
@@ -45,17 +42,15 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.896798 ms
+UnloadTime: 0.880005 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.
-abort_threads: Failed aborting id: 0x7d4264864640, mono_thread_manage will ignore it
-
 Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 552 frames, [16.0 KB-32.0 KB]: 9 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 5373 frames, [16.0 KB-32.0 KB]: 91 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
@@ -171,22 +166,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 36
+  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]: 562 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 5465 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.4 MB
+      Peak Allocated memory 7.2 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 562 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 5465 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.9 MB
+      Peak Allocated memory 17.3 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -215,13 +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]: 427 frames, [64.0 KB-128.0 KB]: 135 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 3505 frames, [64.0 KB-128.0 KB]: 1960 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 66.4 KB
+      Peak Allocated memory 67.7 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 562 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5465 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -233,13 +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]: 562 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5465 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]: 561 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5464 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
@@ -251,13 +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]: 562 frames
+      Peak usage frame count: [0-1.0 KB]: 5465 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]: 562 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 5465 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -1,40 +1,375 @@
 {
     "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 0.9619103074073792,
+            "min": 0.9619103074073792,
+            "max": 2.8682756423950195,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 9216.0625,
+            "min": 9216.0625,
+            "max": 29374.01171875,
+            "count": 20
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 199984.0,
+            "min": 9952.0,
+            "max": 199984.0,
+            "count": 20
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 199984.0,
+            "min": 9952.0,
+            "max": 199984.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 11.916253089904785,
+            "min": 0.26223844289779663,
+            "max": 11.943327903747559,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2323.66943359375,
+            "min": 50.87425994873047,
+            "max": 2436.43896484375,
+            "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": 8756.0,
+            "max": 10945.0,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.07064844631160809,
+            "min": 0.06045420648426765,
+            "max": 0.07321314640598846,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.28259378524643236,
+            "min": 0.2564524323291456,
+            "max": 0.3660657320299423,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.1791175969456341,
+            "min": 0.11523861722454574,
+            "max": 0.27982308069864914,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.7164703877825364,
+            "min": 0.460954468898183,
+            "max": 1.3991154034932456,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 8.082097306000005e-06,
+            "min": 8.082097306000005e-06,
+            "max": 0.000291882002706,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 3.232838922400002e-05,
+            "min": 3.232838922400002e-05,
+            "max": 0.00138516003828,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10269400000000001,
+            "min": 0.10269400000000001,
+            "max": 0.19729400000000002,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.41077600000000003,
+            "min": 0.41077600000000003,
+            "max": 0.96172,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.0001444306000000001,
+            "min": 0.0001444306000000001,
+            "max": 0.0048649706,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0005777224000000004,
+            "min": 0.0005777224000000004,
+            "max": 0.023089828,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 22.818181818181817,
+            "min": 3.409090909090909,
+            "max": 23.818181818181817,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1004.0,
+            "min": 150.0,
+            "max": 1290.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 22.818181818181817,
+            "min": 3.409090909090909,
+            "max": 23.818181818181817,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1004.0,
+            "min": 150.0,
+            "max": 1290.0,
+            "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": "1703604490",
+        "start_time_seconds": "1703604744",
         "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 --run-id=SnowballTarget1 --resume --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.1.2+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1703604550"
+        "end_time_seconds": "1703605186"
     },
-    "total": 60.218964698000036,
+    "total": 442.4196425240002,
     "count": 1,
-    "self": 0.010208830000010494,
+    "self": 0.5831587689999651,
     "children": {
         "run_training.setup": {
-            "total": 0.04731121199984045,
+            "total": 0.07132370299996182,
             "count": 1,
-            "self": 0.04731121199984045
+            "self": 0.07132370299996182
         },
         "TrainerController.start_learning": {
-            "total": 60.161444656000185,
+            "total": 441.7651600520003,
             "count": 1,
-            "self": 0.00011890700034200563,
+            "self": 0.5767614159717596,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 60.16126940000004,
+                    "total": 2.5750052870002946,
+                    "count": 1,
+                    "self": 2.5750052870002946
+                },
+                "TrainerController.advance": {
+                    "total": 438.47794382902794,
+                    "count": 18216,
+                    "self": 0.2715893050194609,
+                    "children": {
+                        "env_step": {
+                            "total": 438.2063545240085,
+                            "count": 18216,
+                            "self": 289.2228420800707,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 148.69773202094711,
+                                    "count": 18216,
+                                    "self": 1.4530100589499853,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 147.24472196199713,
+                                            "count": 18216,
+                                            "self": 147.24472196199713
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.2857804229906833,
+                                    "count": 18216,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 440.4255836120101,
+                                            "count": 18216,
+                                            "is_parallel": true,
+                                            "self": 215.97380556803319,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.002683485000034125,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006360020011015877,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.002047482998932537,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.002047482998932537
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.036522253999919485,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006443729994316527,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0004497050003919867,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004497050003919867
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.033549489000051835,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.033549489000051835
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0018786870000440103,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003846819995487749,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0014940050004952354,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0014940050004952354
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 224.4517780439769,
+                                                    "count": 18215,
+                                                    "is_parallel": true,
+                                                    "self": 10.452371109970954,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 5.2891745199963225,
+                                                            "count": 18215,
+                                                            "is_parallel": true,
+                                                            "self": 5.2891745199963225
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 175.69493266398422,
+                                                            "count": 18215,
+                                                            "is_parallel": true,
+                                                            "self": 175.69493266398422
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 33.015299750025406,
+                                                            "count": 18215,
+                                                            "is_parallel": true,
+                                                            "self": 6.147425217900491,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 26.867874532124915,
+                                                                    "count": 182150,
+                                                                    "is_parallel": true,
+                                                                    "self": 26.867874532124915
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.0001335990000370657,
                     "count": 1,
-                    "self": 60.16126940000004
+                    "self": 0.0001335990000370657,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 433.12787389409505,
+                                    "count": 661099,
+                                    "is_parallel": true,
+                                    "self": 13.968666580098215,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 239.13842157599856,
+                                            "count": 661099,
+                                            "is_parallel": true,
+                                            "self": 238.34902952899847,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 0.7893920470000921,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 0.7893920470000921
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 180.02078573799827,
+                                            "count": 90,
+                                            "is_parallel": true,
+                                            "self": 56.372759893011334,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 123.64802584498693,
+                                                    "count": 4587,
+                                                    "is_parallel": true,
+                                                    "self": 123.64802584498693
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
                 },
                 "TrainerController._save_models": {
-                    "total": 5.6348999805777567e-05,
+                    "total": 0.1353159210002559,
                     "count": 1,
-                    "self": 5.6348999805777567e-05
+                    "self": 0.0012274980003894598,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.13408842299986645,
+                            "count": 1,
+                            "self": 0.13408842299986645
+                        }
+                    }
                 }
             }
         }

run_logs/training_status.json

@@ -2,58 +2,58 @@
     "SnowballTarget": {
         "checkpoints": [
             {
-                "steps": 4976,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-4976.onnx",
-                "reward": 2.8181818181818183,
-                "creation_time": 1703602867.8061154,
+                "steps": 49936,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 14.909090909090908,
+                "creation_time": 1703604858.9500785,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-4976.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-49936.pt"
                 ]
             },
             {
-                "steps": 9952,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-9952.onnx",
-                "reward": 5.545454545454546,
-                "creation_time": 1703602879.1417527,
+                "steps": 99960,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 20.272727272727273,
+                "creation_time": 1703604967.0331597,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-9952.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-99960.pt"
                 ]
             },
             {
-                "steps": 14992,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-14992.onnx",
-                "reward": 4.545454545454546,
-                "creation_time": 1703602890.295999,
+                "steps": 149984,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 23.0,
+                "creation_time": 1703605075.782132,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-14992.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-149984.pt"
                 ]
             },
             {
-                "steps": 19992,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-19992.onnx",
-                "reward": 6.090909090909091,
-                "creation_time": 1703602901.5272164,
+                "steps": 199984,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 22.545454545454547,
+                "creation_time": 1703605186.0410604,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-19992.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.pt"
                 ]
             },
             {
-                "steps": 20376,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-20376.onnx",
-                "reward": 6.090909090909091,
-                "creation_time": 1703602901.6693842,
+                "steps": 200112,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 22.545454545454547,
+                "creation_time": 1703605186.3582025,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-20376.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 20376,
-            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 6.090909090909091,
-            "creation_time": 1703602901.6693842,
+            "steps": 200112,
+            "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
+            "reward": 22.545454545454547,
+            "creation_time": 1703605186.3582025,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-20376.pt"
+                "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
             ]
         }
     },