Add first optimized SnowbalThrower

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6356e309da847a65e9f951ba04d16b3fdae07b649a58a0084d21bad05d01b86c
-size 650646
+oid sha256:4b81e5a96df91d78c21dcb723c7251ce2f2871f7ffc3f783878871bc524523c7
+size 485667

SnowballTarget/SnowballTarget-149984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:569fb1fdb258368cf789aea3cabf267eb06e26124394e9f8c07781b934fa8363
-size 650646
+oid sha256:5fb9cbf686798d422f938a4f0b62c9d4806928721ff2c0209883d62e98d5211f
+size 485667

SnowballTarget/SnowballTarget-149984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aa9717c854dd6ea79d5fff5603c5c726995ba7a7854b4b1ae59d50b38d20716
-size 3849115
+oid sha256:5e3d6fbdd67caf05b08b9fab003ef13f159021b6a519112727a8cc16eda532e0
+size 2864907

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6356e309da847a65e9f951ba04d16b3fdae07b649a58a0084d21bad05d01b86c
-size 650646
+oid sha256:4b81e5a96df91d78c21dcb723c7251ce2f2871f7ffc3f783878871bc524523c7
+size 485667

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41c617192e1774edf01ef033bd48c013bb6804e4f35add2a397db51af4c9f917
-size 3849115
+oid sha256:9eb982a4bd7a43e2aac177971aed0e71eb41ed72b6a6c076dd8e937941baa7a0
+size 2864907

SnowballTarget/SnowballTarget-200112.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6356e309da847a65e9f951ba04d16b3fdae07b649a58a0084d21bad05d01b86c
-size 650646
+oid sha256:9ee20cafa1d60c382e7d72eaa62047d36970e88f502d1e2785d0c50d3221be44
+size 484246

SnowballTarget/SnowballTarget-200112.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52157df04eaa95afb69009a41f91be2263ea65926971d61a0e0c0c38213d62f3
-size 3849115
+oid sha256:e9e0e1f136d779334ca0f3601b3ef4457e1b94569296da22798e060a720905d6
+size 2854491

SnowballTarget/SnowballTarget-200184.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b81e5a96df91d78c21dcb723c7251ce2f2871f7ffc3f783878871bc524523c7
+size 485667

SnowballTarget/SnowballTarget-200184.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2ebdd82b5201968002d9c22ff1b360cea64ead8c34240ddb273d7824f3712d5
+size 2864907

SnowballTarget/SnowballTarget-49936.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d42e33ea4bdc20c100975045524d5c2e15281dbad50a27e815b39a082fdc3ee
-size 650646
+oid sha256:c2e0cb13d4886516279a9d5357cb710a8f35290543600d5096ccefb98b1ed85c
+size 485667

SnowballTarget/SnowballTarget-49936.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ac1a462135a9de75bceb894d6061861f5c9debb032b7961e0368402b25c1d67
-size 3849040
+oid sha256:267aa29e03f202a520aa6519639bf0b81edf1e69ea1a0cf924e5aa4721f81afc
+size 2864816

SnowballTarget/SnowballTarget-99960.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18b5a3eed30fa6c36891884ac1d92929bcf5f3abf35cbcd50bb4b381ae37c667
-size 650646
+oid sha256:070ae9dfdd9a37d0ca6643f1b193e05e5be93d2b8e50e0a2d4010ac900e43268
+size 485667

SnowballTarget/SnowballTarget-99960.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94d540c9e97594238e447583e78f7de135b8005ce66fe10c712efa1380621128
-size 3849040
+oid sha256:7ef0c20427fab80137874adc9a3297a1373c35e565ad17011b9e2c2597341139
+size 2864816

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6161eee3003b88e8be40b2e1067c52b3bb5417b0c630b497006976750a404176
-size 3848290
+oid sha256:7fece49937c7e0c00f62c1148ee66ac3ed4cc03387fc5e5c9ddc7c98a09fed37
+size 2863906

SnowballTarget/events.out.tfevents.1734645838.8ad2915a3aa6.108370.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ffb754f93c71615a64530c764d0f79ec1c043c423455f888986a13294a62c0b
+size 53803

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": 0.3, "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": 0.999, "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": "SnowballTarget7", "initialize_from": null, "load_model": false, "resume": false, "force": true, "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": 129, "buffer_size": 1172, "learning_rate": 0.005848717855174421, "beta": 0.0006933626020387194, "epsilon": 0.0015104254518785796, "lambd": 0.9809480780691303, "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": 168, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.9417107177844183, "strength": 0.9576267730399072, "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": "SnowballTarget11", "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

@@ -3,12 +3,12 @@ behaviors:
   SnowballTarget:
     trainer_type: ppo
     hyperparameters:
-      batch_size: 128
-      buffer_size: 2048
-      learning_rate: 0.0003
-      beta: 0.005
-      epsilon: 0.3
-      lambd: 0.95
+      batch_size: 129
+      buffer_size: 1172
+      learning_rate: 0.005848717855174421
+      beta: 0.0006933626020387194
+      epsilon: 0.0015104254518785796
+      lambd: 0.9809480780691303
       num_epoch: 3
       shared_critic: false
       learning_rate_schedule: linear
@@ -17,16 +17,16 @@ behaviors:
     checkpoint_interval: 50000
     network_settings:
       normalize: false
-      hidden_units: 256
-      num_layers: 2
+      hidden_units: 168
+      num_layers: 3
       vis_encode_type: simple
       memory: null
       goal_conditioning_type: hyper
       deterministic: false
     reward_signals:
       extrinsic:
-        gamma: 0.999
-        strength: 1.0
+        gamma: 0.9417107177844183
+        strength: 0.9576267730399072
         network_settings:
           normalize: false
           hidden_units: 128
@@ -66,7 +66,7 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: SnowballTarget7
+  run_id: SnowballTarget11
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -31,7 +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  0.102 seconds
+- Completed reload, in  0.153 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)
@@ -42,7 +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: 0.803938 ms
+UnloadTime: 0.754228 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.
@@ -50,7 +50,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      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
+      Peak usage frame count: [8.0 KB-16.0 KB]: 5371 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -172,13 +172,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 5465 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 5463 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       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]: 5465 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 5463 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 17.8 MB
@@ -210,13 +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]: 4815 frames, [64.0 KB-128.0 KB]: 650 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5058 frames, [64.0 KB-128.0 KB]: 405 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 66.8 KB
+      Peak Allocated memory 66.4 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 5465 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5463 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -228,13 +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]: 5465 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5463 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]: 5464 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5462 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
@@ -246,13 +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]: 5465 frames
+      Peak usage frame count: [0-1.0 KB]: 5463 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]: 5465 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 5463 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -2,15 +2,15 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 1.0570088624954224,
-            "min": 1.0570088624954224,
-            "max": 2.8655104637145996,
+            "value": 1.6439284086227417,
+            "min": 1.6439284086227417,
+            "max": 2.8902804851531982,
             "count": 20
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 10196.96484375,
-            "min": 10196.96484375,
-            "max": 29408.734375,
+            "value": 15840.89453125,
+            "min": 15840.89453125,
+            "max": 29758.328125,
             "count": 20
         },
         "SnowballTarget.Step.mean": {
@@ -26,15 +26,15 @@
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 72.69437408447266,
-            "min": 0.27865567803382874,
-            "max": 72.69437408447266,
+            "value": 1.9428905248641968,
+            "min": 0.1823497712612152,
+            "max": 1.9428905248641968,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 14175.40234375,
-            "min": 54.0592041015625,
-            "max": 14175.40234375,
+            "value": 378.8636474609375,
+            "min": 35.3758544921875,
+            "max": 380.93072509765625,
             "count": 20
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -50,87 +50,87 @@
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.06966640744696062,
-            "min": 0.06399392901594139,
-            "max": 0.07535856572361024,
+            "value": 0.06267216122382648,
+            "min": 0.055472424205818945,
+            "max": 0.07582000890679685,
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.2786656297878425,
-            "min": 0.2625120740096249,
-            "max": 0.3767928286180512,
+            "value": 0.43870512856678534,
+            "min": 0.3883069694407326,
+            "max": 0.5136208887223149,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 1.0715958010861832,
-            "min": 0.15405998356964476,
-            "max": 1.0715958010861832,
+            "value": 0.136476278666294,
+            "min": 0.058655292562828594,
+            "max": 0.16762607907513521,
             "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 4.286383204344733,
-            "min": 0.616239934278579,
-            "max": 4.4235560064222295,
+            "value": 0.9553339506640579,
+            "min": 0.41058704793980016,
+            "max": 1.1733825535259466,
             "count": 20
         },
         "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 8.130097290000004e-06,
-            "min": 8.130097290000004e-06,
-            "max": 0.000291882002706,
+            "value": 0.00014598409516915355,
+            "min": 0.00014598409516915355,
+            "max": 0.005700316389999796,
             "count": 20
         },
         "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 3.2520389160000015e-05,
-            "min": 3.2520389160000015e-05,
-            "max": 0.00138516003828,
+            "value": 0.0010218886661840748,
+            "min": 0.0010218886661840748,
+            "max": 0.037950692572355366,
             "count": 20
         },
         "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10542,
-            "min": 0.10542,
-            "max": 0.29458799999999996,
+            "value": 0.09754170021927888,
+            "min": 0.004009434256746251,
+            "max": 0.09754170021927888,
             "count": 20
         },
         "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.42168,
-            "min": 0.42168,
-            "max": 1.42344,
+            "value": 0.6827919015349522,
+            "min": 0.024056605540477505,
+            "max": 0.6827919015349522,
             "count": 20
         },
         "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.00014522900000000006,
-            "min": 0.00014522900000000006,
-            "max": 0.0048649706,
+            "value": 2.7056730546886436e-05,
+            "min": 2.7056730546886436e-05,
+            "max": 0.0006760234149496571,
             "count": 20
         },
         "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.0005809160000000002,
-            "min": 0.0005809160000000002,
-            "max": 0.023089828,
+            "value": 0.00018939711382820506,
+            "min": 0.00018939711382820506,
+            "max": 0.00450414858310068,
             "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 24.522727272727273,
-            "min": 3.3863636363636362,
-            "max": 24.84090909090909,
+            "value": 23.386363636363637,
+            "min": 2.6545454545454548,
+            "max": 23.386363636363637,
             "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1079.0,
-            "min": 149.0,
-            "max": 1350.0,
+            "value": 1029.0,
+            "min": 124.0,
+            "max": 1227.0,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 24.522727272727273,
-            "min": 3.3863636363636362,
-            "max": 24.84090909090909,
+            "value": 22.395407249981705,
+            "min": 2.54206375208768,
+            "max": 22.395407249981705,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1079.0,
-            "min": 149.0,
-            "max": 1350.0,
+            "value": 985.3979189991951,
+            "min": 118.74571794271469,
+            "max": 1175.0080181956291,
             "count": 20
         },
         "SnowballTarget.IsTraining.mean": {
@@ -148,67 +148,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1734627193",
+        "start_time_seconds": "1734645837",
         "python_version": "3.10.12 (main, Nov  6 2024, 20:22:13) [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=SnowballTarget7 --no-graphics --force",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget11 --no-graphics --force",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.5.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1734627701"
+        "end_time_seconds": "1734646329"
     },
-    "total": 508.76645837400065,
+    "total": 492.4546862169991,
     "count": 1,
-    "self": 0.8534272899996722,
+    "self": 0.5267043589992682,
     "children": {
         "run_training.setup": {
-            "total": 0.07397535600011906,
+            "total": 0.10980674199890927,
             "count": 1,
-            "self": 0.07397535600011906
+            "self": 0.10980674199890927
         },
         "TrainerController.start_learning": {
-            "total": 507.83905572800086,
+            "total": 491.81817511600093,
             "count": 1,
-            "self": 0.7728106421272969,
+            "self": 0.8021783462972962,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.1475500619999366,
+                    "total": 2.2097316759973182,
                     "count": 1,
-                    "self": 2.1475500619999366
+                    "self": 2.2097316759973182
                 },
                 "TrainerController.advance": {
-                    "total": 504.79576474787336,
-                    "count": 18216,
-                    "self": 0.35199509884296276,
+                    "total": 488.7256403117026,
+                    "count": 18209,
+                    "self": 0.372184840925911,
                     "children": {
                         "env_step": {
-                            "total": 504.4437696490304,
-                            "count": 18216,
-                            "self": 390.56604933808103,
+                            "total": 488.3534554707767,
+                            "count": 18209,
+                            "self": 361.6315583955293,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 113.51530026599266,
-                                    "count": 18216,
-                                    "self": 1.686062709853104,
+                                    "total": 126.34392291447875,
+                                    "count": 18209,
+                                    "self": 2.022507725367177,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 111.82923755613956,
-                                            "count": 18216,
-                                            "self": 111.82923755613956
+                                            "total": 124.32141518911158,
+                                            "count": 18209,
+                                            "self": 124.32141518911158
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.362420044956707,
-                                    "count": 18216,
+                                    "total": 0.37797416076864465,
+                                    "count": 18209,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 506.3777025611553,
-                                            "count": 18216,
+                                            "total": 490.0476761838072,
+                                            "count": 18209,
                                             "is_parallel": true,
-                                            "self": 237.44028296412762,
+                                            "self": 216.11597017761596,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0025272900002164533,
+                                                            "total": 0.0025727829997777008,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0007105319982656511,
+                                                            "self": 0.0007713410050200764,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0018167580019508023,
+                                                                    "total": 0.0018014419947576243,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0018167580019508023
+                                                                    "self": 0.0018014419947576243
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.0440442629997051,
+                                                            "total": 0.04092625699922792,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0007998729997780174,
+                                                            "self": 0.0008045159993343987,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004353680005806382,
+                                                                    "total": 0.000446805999672506,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004353680005806382
+                                                                    "self": 0.000446805999672506
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04050789199936844,
+                                                                    "total": 0.037390420999145135,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04050789199936844
+                                                                    "self": 0.037390420999145135
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.002301129999978002,
+                                                                    "total": 0.002284514001075877,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004276689996913774,
+                                                                    "self": 0.0004699480050476268,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0018734610002866248,
+                                                                            "total": 0.00181456599602825,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0018734610002866248
+                                                                            "self": 0.00181456599602825
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 268.93741959702766,
-                                                    "count": 18215,
+                                                    "total": 273.93170600619123,
+                                                    "count": 18208,
                                                     "is_parallel": true,
-                                                    "self": 12.26184202843433,
+                                                    "self": 12.34132495736776,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 6.364484995800922,
-                                                            "count": 18215,
+                                                            "total": 6.28572836901003,
+                                                            "count": 18208,
                                                             "is_parallel": true,
-                                                            "self": 6.364484995800922
+                                                            "self": 6.28572836901003
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 210.22814889385972,
-                                                            "count": 18215,
+                                                            "total": 215.35456801667533,
+                                                            "count": 18208,
                                                             "is_parallel": true,
-                                                            "self": 210.22814889385972
+                                                            "self": 215.35456801667533
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 40.08294367893268,
-                                                            "count": 18215,
+                                                            "total": 39.950084663138114,
+                                                            "count": 18208,
                                                             "is_parallel": true,
-                                                            "self": 7.758650228773149,
+                                                            "self": 7.68151135008884,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 32.32429345015953,
-                                                                    "count": 182150,
+                                                                    "total": 32.268573313049274,
+                                                                    "count": 182080,
                                                                     "is_parallel": true,
-                                                                    "self": 32.32429345015953
+                                                                    "self": 32.268573313049274
                                                                 }
                                                             }
                                                         }
@@ -309,9 +309,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 0.00017435200061299838,
+                    "total": 0.0003680500012706034,
                     "count": 1,
-                    "self": 0.00017435200061299838,
+                    "self": 0.0003680500012706034,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -320,36 +320,36 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 499.1403829611245,
-                                    "count": 673285,
+                                    "total": 485.92623232954793,
+                                    "count": 372338,
                                     "is_parallel": true,
-                                    "self": 14.584482302123433,
+                                    "self": 8.142840825508756,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 267.5230394039954,
-                                            "count": 673285,
+                                            "total": 182.39031493504444,
+                                            "count": 372338,
                                             "is_parallel": true,
-                                            "self": 266.51461972099605,
+                                            "self": 181.79515693904614,
                                             "children": {
                                                 "RLTrainer._checkpoint": {
-                                                    "total": 1.0084196829993743,
+                                                    "total": 0.5951579959983064,
                                                     "count": 4,
                                                     "is_parallel": true,
-                                                    "self": 1.0084196829993743
+                                                    "self": 0.5951579959983064
                                                 }
                                             }
                                         },
                                         "_update_policy": {
-                                            "total": 217.03286125500563,
-                                            "count": 90,
+                                            "total": 295.39307656899473,
+                                            "count": 136,
                                             "is_parallel": true,
-                                            "self": 64.91700181401939,
+                                            "self": 83.54235101915401,
                                             "children": {
                                                 "TorchPPOOptimizer.update": {
-                                                    "total": 152.11585944098624,
-                                                    "count": 4584,
+                                                    "total": 211.85072554984072,
+                                                    "count": 4353,
                                                     "is_parallel": true,
-                                                    "self": 152.11585944098624
+                                                    "self": 211.85072554984072
                                                 }
                                             }
                                         }
@@ -360,14 +360,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.12275592399964808,
+                    "total": 0.08025673200245365,
                     "count": 1,
-                    "self": 0.0026623749999998836,
+                    "self": 0.0012775960021826904,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.12009354899964819,
+                            "total": 0.07897913600027096,
                             "count": 1,
-                            "self": 0.12009354899964819
+                            "self": 0.07897913600027096
                         }
                     }
                 }

run_logs/training_status.json

@@ -3,57 +3,57 @@
         "checkpoints": [
             {
                 "steps": 49936,
-                "file_path": "results/SnowballTarget7/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 13.272727272727273,
-                "creation_time": 1734627321.351407,
+                "file_path": "results/SnowballTarget11/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": null,
+                "creation_time": 1734645962.7687764,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget7/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/SnowballTarget11/SnowballTarget/SnowballTarget-49936.pt"
                 ]
             },
             {
                 "steps": 99960,
-                "file_path": "results/SnowballTarget7/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 22.0,
-                "creation_time": 1734627447.0557241,
+                "file_path": "results/SnowballTarget11/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": null,
+                "creation_time": 1734646085.8705854,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget7/SnowballTarget/SnowballTarget-99960.pt"
+                    "results/SnowballTarget11/SnowballTarget/SnowballTarget-99960.pt"
                 ]
             },
             {
                 "steps": 149984,
-                "file_path": "results/SnowballTarget7/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 22.272727272727273,
-                "creation_time": 1734627573.2238097,
+                "file_path": "results/SnowballTarget11/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 17.272727272727273,
+                "creation_time": 1734646206.798937,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget7/SnowballTarget/SnowballTarget-149984.pt"
+                    "results/SnowballTarget11/SnowballTarget/SnowballTarget-149984.pt"
                 ]
             },
             {
                 "steps": 199984,
-                "file_path": "results/SnowballTarget7/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 23.818181818181817,
-                "creation_time": 1734627700.8767295,
+                "file_path": "results/SnowballTarget11/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": null,
+                "creation_time": 1734646329.3024094,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget7/SnowballTarget/SnowballTarget-199984.pt"
+                    "results/SnowballTarget11/SnowballTarget/SnowballTarget-199984.pt"
                 ]
             },
             {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget7/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 23.818181818181817,
-                "creation_time": 1734627701.0183313,
+                "steps": 200184,
+                "file_path": "results/SnowballTarget11/SnowballTarget/SnowballTarget-200184.onnx",
+                "reward": 23.88888888888889,
+                "creation_time": 1734646329.4213703,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget7/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/SnowballTarget11/SnowballTarget/SnowballTarget-200184.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 200112,
-            "file_path": "results/SnowballTarget7/SnowballTarget.onnx",
-            "reward": 23.818181818181817,
-            "creation_time": 1734627701.0183313,
+            "steps": 200184,
+            "file_path": "results/SnowballTarget11/SnowballTarget.onnx",
+            "reward": 23.88888888888889,
+            "creation_time": 1734646329.4213703,
             "auxillary_file_paths": [
-                "results/SnowballTarget7/SnowballTarget/SnowballTarget-200112.pt"
+                "results/SnowballTarget11/SnowballTarget/SnowballTarget-200184.pt"
             ]
         }
     },