First Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d53c31fb07fbed8774b85cfc7152ccf7507a01eb7666ad36ce6c578c9b7e1b1e
+oid sha256:535bae02ab217c2ae233491f22a90f9da14257ad02f1fcf3e608ece560a1ed91
 size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02b6f032fef328725757e38a55a764acad73712c7a9f39ff9dba0d588c35188f
+oid sha256:4f5c25dfbbb70e6caa542889a595eda772a5e0a3cdd3f154c7a49524db3acd61
 size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6043378c34ad7bfb4e2dba2b77f733699907964a94a84443577ee1c04b13da2
+oid sha256:48d3565c15b2677d71ef8e062e8720cce1e192655fe477aad5d9b039b13b51ce
 size 3850075

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d53c31fb07fbed8774b85cfc7152ccf7507a01eb7666ad36ce6c578c9b7e1b1e
+oid sha256:535bae02ab217c2ae233491f22a90f9da14257ad02f1fcf3e608ece560a1ed91
 size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdb8be767190b567242e6c9022ceecf14039cde6cdf8d1419a832ff99f7d59aa
+oid sha256:7601510b05059f78af7c9fb8a3912a459a3b37f93c29f51f2c0c744d3f0a0b11
 size 3850075

SnowballTarget/SnowballTarget-200112.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d53c31fb07fbed8774b85cfc7152ccf7507a01eb7666ad36ce6c578c9b7e1b1e
+oid sha256:535bae02ab217c2ae233491f22a90f9da14257ad02f1fcf3e608ece560a1ed91
 size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba2ca63b9626343f889c0af01f847a514034afd9ec8fb50b4b62e38618d0221b
+oid sha256:3512c8123a74048a278bcef04b71d6ce7d830445b8fe96e12fd378c606ec7199
 size 3850075

SnowballTarget/SnowballTarget-49936.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fef76f8d697cf83e8053be1a34cd52054667b561b3586c83ac040944856dcb17
+oid sha256:49d6343c0efe58a6f3b3125b7a1f7c1d1f366c03870a8196808d5781b282640a
 size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fa0c5a79420b59f1e342e279420d4d5b1265410c45772f0b8a377727c260318
+oid sha256:b5c41d496d0576c41ce13eca98c6b21904130120c235f8bf3696a576189b99d2
 size 3850000

SnowballTarget/SnowballTarget-99960.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2c3358db10d2d904b4d6222123870bbe6d91f09ba1a1a56aaa46ff3e5e495a2
+oid sha256:7c0ff36ced7856ea1f3a67511e453396511d372ab2b3d7f5c3100f20920b2a2e
 size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91a304d654701e939c8a701ecc0fa8a3ed2577d6a5c84e0e039101eed7763d75
+oid sha256:be307f36c84a51cb20ab5e013203bfd7fa21d24aa113c066df50a7805dcd1e77
 size 3850000

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cfa14e1509fd2c973ef5b0d53440fdc52611529b4a9dafcb8158d66689e6808
+oid sha256:3317d42e91e3d2b1dd6e911a70d25514ca2824193f6609d48cb1f491285920be
 size 3849250

SnowballTarget/events.out.tfevents.1708079523.e4fd9420214f.1594.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d52bbcc01d37f5fea0d78b318fc624df6ae1aba36dc258118052348a31d1c298
+size 28879

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": 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": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -70,7 +70,7 @@ checkpoint_settings:
   initialize_from: null
   load_model: false
   resume: false
-  force: false
+  force: true
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -1,12 +1,9 @@
-Mono path[0] = '/workspaces/reinforcement-learning-course/course/unity5/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
-Mono config path = '/workspaces/reinforcement-learning-course/course/unity5/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
+Mono path[0] = '/workspaces/reinforcement-learning-course/course/unit5/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/workspaces/reinforcement-learning-course/course/unit5/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 /workspaces/reinforcement-learning-course/course/unity5/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
+[Subsystems] Discovering subsystems at path /workspaces/reinforcement-learning-course/course/unit5/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
 Forcing GfxDevice: Null
 GfxDevice: creating device client; threaded=0; jobified=0
 NullGfxDevice:
@@ -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  0.042 seconds
+- Completed reload, in  0.039 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: 0.420478 ms
+UnloadTime: 0.408071 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 16 worker threads for Enlighten.
@@ -98,12 +95,12 @@ Memory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 3.6 KB
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 14]
+    [ALLOC_TEMP_Job.Worker 17]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 3.6 KB
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 17]
+    [ALLOC_TEMP_Job.Worker 14]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 3.6 KB
@@ -193,12 +190,12 @@ Memory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 3.6 KB
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 26]
+    [ALLOC_TEMP_Job.Worker 21]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 3.6 KB
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 21]
+    [ALLOC_TEMP_Job.Worker 26]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 3.6 KB
@@ -208,7 +205,7 @@ Memory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 3.6 KB
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 14]
+    [ALLOC_TEMP_Background Job.Worker 9]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -218,7 +215,7 @@ Memory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 3.6 KB
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
+    [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -293,22 +290,22 @@ Memory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 3.6 KB
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 15]
+    [ALLOC_TEMP_Job.Worker 24]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 3.6 KB
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 24]
+    [ALLOC_TEMP_Job.Worker 15]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 3.6 KB
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 19]
+    [ALLOC_TEMP_Job.Worker 12]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 3.6 KB
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 12]
+    [ALLOC_TEMP_Job.Worker 19]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 3.6 KB
@@ -316,10 +313,10 @@ Memory Statistics:
     [ALLOC_TEMP_Loading.AsyncRead]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 292 B
+      Peak Allocated Bytes 290 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 41
+  Peak main deferred allocation count 40
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
@@ -334,7 +331,7 @@ Memory Statistics:
       Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.6 MB
+      Peak Allocated memory 17.5 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -363,10 +360,10 @@ 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]: 4171 frames, [64.0 KB-128.0 KB]: 1290 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 4530 frames, [64.0 KB-128.0 KB]: 931 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 67.3 KB
+      Peak Allocated memory 66.8 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
       Peak usage frame count: [32.0 KB-64.0 KB]: 5461 frames

run_logs/timers.json

@@ -2,15 +2,15 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 0.9938374161720276,
-            "min": 0.9938374161720276,
-            "max": 2.867473840713501,
+            "value": 0.9192315340042114,
+            "min": 0.9192315340042114,
+            "max": 2.8722503185272217,
             "count": 20
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 9521.9560546875,
-            "min": 9521.9560546875,
-            "max": 29460.42578125,
+            "value": 8797.0458984375,
+            "min": 8797.0458984375,
+            "max": 29477.904296875,
             "count": 20
         },
         "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 11.73255443572998,
-            "min": 0.5038750767707825,
-            "max": 11.73255443572998,
+            "value": 12.675583839416504,
+            "min": 0.1918199062347412,
+            "max": 12.675583839416504,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2287.84814453125,
-            "min": 97.75177001953125,
-            "max": 2379.9619140625,
+            "value": 2471.73876953125,
+            "min": 37.21306228637695,
+            "max": 2572.742431640625,
             "count": 20
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -49,34 +49,58 @@
             "max": 10945.0,
             "count": 20
         },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 25.09090909090909,
+            "min": 3.159090909090909,
+            "max": 25.09090909090909,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1104.0,
+            "min": 139.0,
+            "max": 1367.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 25.09090909090909,
+            "min": 3.159090909090909,
+            "max": 25.09090909090909,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1104.0,
+            "min": 139.0,
+            "max": 1367.0,
+            "count": 20
+        },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.07142672198881651,
-            "min": 0.06495762881868537,
-            "max": 0.07605622582309925,
+            "value": 0.06375053759763308,
+            "min": 0.06285092248184738,
+            "max": 0.07566402355555957,
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.28570688795526605,
-            "min": 0.2598305152747415,
-            "max": 0.3785982645760455,
+            "value": 0.2550021503905323,
+            "min": 0.2550021503905323,
+            "max": 0.37832011777779784,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.19691719326610657,
-            "min": 0.12123059188974472,
-            "max": 0.2905612743514426,
+            "value": 0.20342359691858292,
+            "min": 0.10652379825820818,
+            "max": 0.2963242155079748,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.7876687730644263,
-            "min": 0.4849223675589789,
-            "max": 1.4071116996746436,
+            "value": 0.8136943876743317,
+            "min": 0.4260951930328327,
+            "max": 1.481621077539874,
             "count": 20
         },
         "SnowballTarget.Policy.LearningRate.mean": {
             "value": 8.082097306000005e-06,
             "min": 8.082097306000005e-06,
-            "max": 0.000291882002706,
+            "max": 0.00029184900271699997,
             "count": 20
         },
         "SnowballTarget.Policy.LearningRate.sum": {
@@ -88,7 +112,7 @@
         "SnowballTarget.Policy.Epsilon.mean": {
             "value": 0.10269400000000001,
             "min": 0.10269400000000001,
-            "max": 0.19729400000000002,
+            "max": 0.19728300000000004,
             "count": 20
         },
         "SnowballTarget.Policy.Epsilon.sum": {
@@ -100,7 +124,7 @@
         "SnowballTarget.Policy.Beta.mean": {
             "value": 0.0001444306000000001,
             "min": 0.0001444306000000001,
-            "max": 0.0048649706,
+            "max": 0.0048644217,
             "count": 20
         },
         "SnowballTarget.Policy.Beta.sum": {
@@ -109,30 +133,6 @@
             "max": 0.023089828,
             "count": 20
         },
-        "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 23.15909090909091,
-            "min": 3.5,
-            "max": 23.527272727272727,
-            "count": 20
-        },
-        "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1019.0,
-            "min": 154.0,
-            "max": 1294.0,
-            "count": 20
-        },
-        "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 23.15909090909091,
-            "min": 3.5,
-            "max": 23.527272727272727,
-            "count": 20
-        },
-        "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1019.0,
-            "min": 154.0,
-            "max": 1294.0,
-            "count": 20
-        },
         "SnowballTarget.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
@@ -148,67 +148,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1708005961",
+        "start_time_seconds": "1708079522",
         "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",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.2.0+cu121",
-        "numpy_version": "1.23.5",
-        "end_time_seconds": "1708006338"
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1708079916"
     },
-    "total": 376.8408562250006,
+    "total": 393.62493889100006,
     "count": 1,
-    "self": 0.22000378999655368,
+    "self": 0.2703265179952723,
     "children": {
         "run_training.setup": {
-            "total": 0.01569223200203851,
+            "total": 0.01448039500246523,
             "count": 1,
-            "self": 0.01569223200203851
+            "self": 0.01448039500246523
         },
         "TrainerController.start_learning": {
-            "total": 376.605160203002,
+            "total": 393.3401319780023,
             "count": 1,
-            "self": 0.3858108900967636,
+            "self": 0.43650310122029623,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 1.2901278770004865,
+                    "total": 1.105587543999718,
                     "count": 1,
-                    "self": 1.2901278770004865
+                    "self": 1.105587543999718
                 },
                 "TrainerController.advance": {
-                    "total": 374.87211922190545,
-                    "count": 18202,
-                    "self": 0.1873388351741596,
+                    "total": 391.7385997017773,
+                    "count": 18201,
+                    "self": 0.20346960727329133,
                     "children": {
                         "env_step": {
-                            "total": 374.6847803867313,
-                            "count": 18202,
-                            "self": 216.90356242378766,
+                            "total": 391.535130094504,
+                            "count": 18201,
+                            "self": 244.68716851486533,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 157.56626354416585,
-                                    "count": 18202,
-                                    "self": 1.112029014449945,
+                                    "total": 146.6104092521491,
+                                    "count": 18201,
+                                    "self": 1.1776646150974557,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 156.4542345297159,
-                                            "count": 18202,
-                                            "self": 156.4542345297159
+                                            "total": 145.43274463705166,
+                                            "count": 18201,
+                                            "self": 145.43274463705166
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.2149544187777792,
-                                    "count": 18202,
+                                    "total": 0.23755232748953858,
+                                    "count": 18201,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 375.8842824683743,
-                                            "count": 18202,
+                                            "total": 392.62108338120015,
+                                            "count": 18201,
                                             "is_parallel": true,
-                                            "self": 215.02137959124957,
+                                            "self": 205.60812447789795,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0013307830013218336,
+                                                            "total": 0.0012301889946684241,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00047157200242509134,
+                                                            "self": 0.000406236998969689,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0008592109988967422,
+                                                                    "total": 0.0008239519956987351,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0008592109988967422
+                                                                    "self": 0.0008239519956987351
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.020179667000775225,
+                                                            "total": 0.023591150995343924,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00019189000522601418,
+                                                            "self": 0.0002002689871005714,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00014331700003822334,
+                                                                    "total": 0.0005734540027333423,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00014331700003822334
+                                                                    "self": 0.0005734540027333423
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.01915219899819931,
+                                                                    "total": 0.022032102999219205,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.01915219899819931
+                                                                    "self": 0.022032102999219205
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0006922609973116778,
+                                                                    "total": 0.0007853250062908046,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00017056699653039686,
+                                                                    "self": 0.00019681201229104772,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0005216940007812809,
+                                                                            "total": 0.0005885129939997569,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0005216940007812809
+                                                                            "self": 0.0005885129939997569
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 160.86290287712472,
-                                                    "count": 18201,
+                                                    "total": 187.0129589033022,
+                                                    "count": 18200,
                                                     "is_parallel": true,
-                                                    "self": 3.50999104643779,
+                                                    "self": 3.8799755034633563,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 2.147183898217918,
-                                                            "count": 18201,
+                                                            "total": 2.39522441214649,
+                                                            "count": 18200,
                                                             "is_parallel": true,
-                                                            "self": 2.147183898217918
+                                                            "self": 2.39522441214649
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 145.64208123623393,
-                                                            "count": 18201,
+                                                            "total": 168.77685234500677,
+                                                            "count": 18200,
                                                             "is_parallel": true,
-                                                            "self": 145.64208123623393
+                                                            "self": 168.77685234500677
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 9.563646696235082,
-                                                            "count": 18201,
+                                                            "total": 11.960906642685586,
+                                                            "count": 18200,
                                                             "is_parallel": true,
-                                                            "self": 2.235202875788673,
+                                                            "self": 2.6766800949480967,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 7.3284438204464095,
-                                                                    "count": 182010,
+                                                                    "total": 9.28422654773749,
+                                                                    "count": 182000,
                                                                     "is_parallel": true,
-                                                                    "self": 7.3284438204464095
+                                                                    "self": 9.28422654773749
                                                                 }
                                                             }
                                                         }
@@ -309,9 +309,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 0.00010352599929319695,
+                    "total": 8.46290058689192e-05,
                     "count": 1,
-                    "self": 0.00010352599929319695,
+                    "self": 8.46290058689192e-05,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -320,36 +320,36 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 373.14890932762137,
-                                    "count": 332617,
+                                    "total": 389.4141271024273,
+                                    "count": 344416,
                                     "is_parallel": true,
-                                    "self": 5.223721549289621,
+                                    "self": 6.619416726120107,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 209.01437588933914,
-                                            "count": 332617,
+                                            "total": 216.45801907726127,
+                                            "count": 344416,
                                             "is_parallel": true,
-                                            "self": 208.58555328633884,
+                                            "self": 216.09312064325786,
                                             "children": {
                                                 "RLTrainer._checkpoint": {
-                                                    "total": 0.42882260300029884,
+                                                    "total": 0.3648984340034076,
                                                     "count": 4,
                                                     "is_parallel": true,
-                                                    "self": 0.42882260300029884
+                                                    "self": 0.3648984340034076
                                                 }
                                             }
                                         },
                                         "_update_policy": {
-                                            "total": 158.9108118889926,
+                                            "total": 166.33669129904592,
                                             "count": 90,
                                             "is_parallel": true,
-                                            "self": 23.660605850047432,
+                                            "self": 31.018204163425253,
                                             "children": {
                                                 "TorchPPOOptimizer.update": {
-                                                    "total": 135.25020603894518,
+                                                    "total": 135.31848713562067,
                                                     "count": 4587,
                                                     "is_parallel": true,
-                                                    "self": 135.25020603894518
+                                                    "self": 135.31848713562067
                                                 }
                                             }
                                         }
@@ -360,14 +360,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.0569986880000215,
+                    "total": 0.059357001999160275,
                     "count": 1,
-                    "self": 0.0006153909998829477,
+                    "self": 0.0006415859970729798,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.056383297000138555,
+                            "total": 0.058715416002087295,
                             "count": 1,
-                            "self": 0.056383297000138555
+                            "self": 0.058715416002087295
                         }
                     }
                 }

run_logs/training_status.json

@@ -4,8 +4,8 @@
             {
                 "steps": 49936,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 13.909090909090908,
-                "creation_time": 1708006054.7001042,
+                "reward": 13.181818181818182,
+                "creation_time": 1708079619.5195909,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
                 ]
@@ -13,8 +13,8 @@
             {
                 "steps": 99960,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 20.181818181818183,
-                "creation_time": 1708006150.1190605,
+                "reward": 21.363636363636363,
+                "creation_time": 1708079715.7734494,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
                 ]
@@ -22,8 +22,8 @@
             {
                 "steps": 149984,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 22.454545454545453,
-                "creation_time": 1708006244.0212195,
+                "reward": 24.636363636363637,
+                "creation_time": 1708079815.9141054,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
                 ]
@@ -31,8 +31,8 @@
             {
                 "steps": 199984,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 23.818181818181817,
-                "creation_time": 1708006337.885693,
+                "reward": 25.454545454545453,
+                "creation_time": 1708079916.1908214,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
                 ]
@@ -40,8 +40,8 @@
             {
                 "steps": 200112,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 23.818181818181817,
-                "creation_time": 1708006337.9675162,
+                "reward": 25.454545454545453,
+                "creation_time": 1708079916.2722778,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
                 ]
@@ -50,8 +50,8 @@
         "final_checkpoint": {
             "steps": 200112,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 23.818181818181817,
-            "creation_time": 1708006337.9675162,
+            "reward": 25.454545454545453,
+            "creation_time": 1708079916.2722778,
             "auxillary_file_paths": [
                 "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
             ]