First Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:868494452fb6fdcfc260714471d438cd45c3e9cfc8e31abde38b37a847f75433
-size 649740
+oid sha256:fe10425c7ba2a31d017136c88d98b2fa6b575142d1f7b7b4143b4680d9007336
+size 331587

SnowballTarget/SnowballTarget-159936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cf88436e0df408d508203ace1057b8bb04ab01cb50ad2bb98eaf62aa9cd3809
+size 331587

SnowballTarget/SnowballTarget-159936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5d50d047019f79083f023e8f2ed24cf731c2299ce8d3817d8192dc044c7defc
+size 1944651

SnowballTarget/SnowballTarget-164992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcff18b3b28754aff54b7a4e58768f4ac503b545cdf246dd338a160b1b0fc188
+size 331587

SnowballTarget/SnowballTarget-164992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4679a54e7571e556d3d9e94c07d43da25cef122448a6eca4c3030018f634462
+size 1944651

SnowballTarget/SnowballTarget-169976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8170b26105a0c19a76536d579315908d083ae90aa4de25a500cb98b29e9e81b3
+size 331587

SnowballTarget/SnowballTarget-169976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe092c31e0432aeff8d11befd2d98133998f02b823365416b1332d5f4ca99aa3
+size 1944651

SnowballTarget/SnowballTarget-174952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25f19dc17691cefd4805de101c915b795df38d1bf2eff4c7dc989b55d1213f6c
+size 331587

SnowballTarget/SnowballTarget-174952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09308c92d8d823e7ea3235891ec45c90078ea63e023d18401d9fd1302797d55b
+size 1944651

SnowballTarget/SnowballTarget-179992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43bc9a7e16b59fa5f5f00b25b8a4b1eb262a010e2467a2842f5338fbb068f5c1
+size 331587

SnowballTarget/SnowballTarget-179992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55e91f870daf42077c55dcc5affecfe4d9f3e98771211a9cacc10606cded85e5
+size 1944651

SnowballTarget/SnowballTarget-184992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9b49c1ebc076578445f1722c6c2f87e61200ee11aadb6ecbde7b9b83ab0e98d
+size 331587

SnowballTarget/SnowballTarget-184992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13ae5df44706b90305f957fc255bad3e55de5248a3a8fc5fa1942fd3f069433a
+size 1944651

SnowballTarget/SnowballTarget-189968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddd4b343f05d33b97f2225953d5fc910c43b55d75d04c573aa0f7be5e98d60b9
+size 331587

SnowballTarget/SnowballTarget-189968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:155846fb8e8d61fc3d9a0b8554f423772f79732e283063f6ae6e0dd0d62a64de
+size 1944651

SnowballTarget/SnowballTarget-194944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e1fefd1ea1b9c11c7000190412128a3f413cab43bbce1d95e8b193b225e21be
+size 331587

SnowballTarget/SnowballTarget-194944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c84f8a256d5d47138f2788e3bcca8bc30d17740e7505b5de0525e35f3613872
+size 1944651

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe10425c7ba2a31d017136c88d98b2fa6b575142d1f7b7b4143b4680d9007336
+size 331587

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fbd8451ec766b062c52e4aae19665e383366726633fa908ef2f936f69df3711
+size 1944651

SnowballTarget/SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe10425c7ba2a31d017136c88d98b2fa6b575142d1f7b7b4143b4680d9007336
+size 331587

SnowballTarget/SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c12077853d6ef4c41c859e57a8f768002c9904383476b70cc6b3f209f55d180a
+size 1944651

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fe8b1533b7b4cad0b33dfd110560ca0f5111d9f3eb5a2a8d556540b1e58c762
-size 1285666
+oid sha256:0c09373862ad4b317c8359bac5eedc72d244f58ce11c315a750c07508df4c148
+size 1943650

SnowballTarget/events.out.tfevents.1728301473.54244b8d4bdb.22575.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eb03367429de2b8b703298c5a97e84d41868d7eaf748a7d6f35bb79df0178e6
+size 23411

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": 500, "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": 1, "even_checkpoints": false, "max_steps": 2000, "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": 0.0005, "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": 128, "num_layers": 3, "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

@@ -5,7 +5,7 @@ behaviors:
     hyperparameters:
       batch_size: 128
       buffer_size: 2048
-      learning_rate: 0.0003
+      learning_rate: 0.0005
       beta: 0.005
       epsilon: 0.2
       lambd: 0.95
@@ -14,11 +14,11 @@ behaviors:
       learning_rate_schedule: linear
       beta_schedule: linear
       epsilon_schedule: linear
-    checkpoint_interval: 500
+    checkpoint_interval: 5000
     network_settings:
       normalize: false
-      hidden_units: 256
-      num_layers: 2
+      hidden_units: 128
+      num_layers: 3
       vis_encode_type: simple
       memory: null
       goal_conditioning_type: hyper
@@ -36,9 +36,9 @@ behaviors:
           goal_conditioning_type: hyper
           deterministic: false
     init_path: null
-    keep_checkpoints: 1
+    keep_checkpoints: 10
     even_checkpoints: false
-    max_steps: 2000
+    max_steps: 200000
     time_horizon: 64
     summary_freq: 10000
     threaded: true
@@ -66,7 +66,7 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: SnowballTarget1
+  run_id: SnowballTarget2
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/ml-agents/training-envs-executables/linux/Sno
 Mono config path = '/content/ml-agents/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/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  0.110 seconds
+- Completed reload, in  0.250 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: 0.923205 ms
+UnloadTime: 1.277566 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -53,7 +50,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 60 frames, [16.0 KB-32.0 KB]: 1 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 5369 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
@@ -169,19 +166,19 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 25
+  Peak main deferred allocation count 41
     [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]: 62 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 5461 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.4 MB
+      Peak Allocated memory 7.0 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 62 frames
+      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 17.5 MB
@@ -213,13 +210,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 59 frames, [64.0 KB-128.0 KB]: 3 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 4534 frames, [64.0 KB-128.0 KB]: 927 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 65.6 KB
+      Peak Allocated memory 67.3 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 62 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5461 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -231,13 +228,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 62 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5461 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]: 61 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5460 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 MB
@@ -249,13 +246,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 62 frames
+      Peak usage frame count: [0-1.0 KB]: 5461 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]: 62 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 5461 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -1,68 +1,214 @@
 {
     "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 0.8668443560600281,
+            "min": 0.8668443560600281,
+            "max": 2.863755702972412,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 8286.1650390625,
+            "min": 8286.1650390625,
+            "max": 29327.72265625,
+            "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": 12.863457679748535,
+            "min": 0.46224677562713623,
+            "max": 12.863457679748535,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2508.374267578125,
+            "min": 89.67587280273438,
+            "max": 2614.728759765625,
+            "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": 0.06866685939380926,
+            "min": 0.05915796499971561,
+            "max": 0.0760819138952202,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.27466743757523704,
+            "min": 0.255905486122584,
+            "max": 0.38040956947610105,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.18427617409650016,
+            "min": 0.1363371276620812,
+            "max": 0.2557823061943054,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.7371046963860006,
+            "min": 0.5453485106483248,
+            "max": 1.231887838419746,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 1.347009730600001e-05,
+            "min": 1.347009730600001e-05,
+            "max": 0.00048647000270600005,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 5.388038922400004e-05,
+            "min": 5.388038922400004e-05,
+            "max": 0.00230860003828,
+            "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": 25.931818181818183,
+            "min": 3.772727272727273,
+            "max": 25.931818181818183,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1141.0,
+            "min": 166.0,
+            "max": 1395.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 25.931818181818183,
+            "min": 3.772727272727273,
+            "max": 25.931818181818183,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1141.0,
+            "min": 166.0,
+            "max": 1395.0,
+            "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": "1728300425",
+        "start_time_seconds": "1728301472",
         "python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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/SnowballTarget2.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.4.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1728300435"
+        "end_time_seconds": "1728302039"
     },
-    "total": 10.151629304999915,
+    "total": 567.1566313940002,
     "count": 1,
-    "self": 0.5500839290007207,
+    "self": 0.5272754200004783,
     "children": {
         "run_training.setup": {
-            "total": 0.07141084799968667,
+            "total": 0.07268235199990158,
             "count": 1,
-            "self": 0.07141084799968667
+            "self": 0.07268235199990158
         },
         "TrainerController.start_learning": {
-            "total": 9.530134527999508,
+            "total": 566.5566736219998,
             "count": 1,
-            "self": 0.03309734099821071,
+            "self": 0.8787547879746853,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.1958494199998313,
+                    "total": 2.4031638490005207,
                     "count": 1,
-                    "self": 3.1958494199998313
+                    "self": 2.4031638490005207
                 },
                 "TrainerController.advance": {
-                    "total": 6.2154025260006165,
-                    "count": 205,
-                    "self": 0.004557442000077572,
+                    "total": 563.1931225570243,
+                    "count": 18203,
+                    "self": 0.4416712740821822,
                     "children": {
                         "env_step": {
-                            "total": 6.210845084000539,
-                            "count": 205,
-                            "self": 4.490468939015955,
+                            "total": 562.7514512829421,
+                            "count": 18203,
+                            "self": 425.4850428569134,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 1.7159508899858338,
-                                    "count": 205,
-                                    "self": 0.031169303987553576,
+                                    "total": 136.85608094999498,
+                                    "count": 18203,
+                                    "self": 2.2701863251058967,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 1.6847815859982802,
-                                            "count": 205,
-                                            "self": 1.6847815859982802
+                                            "total": 134.58589462488908,
+                                            "count": 18203,
+                                            "self": 134.58589462488908
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.004425254998750461,
-                                    "count": 205,
+                                    "total": 0.4103274760336717,
+                                    "count": 18203,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 9.461348603004808,
-                                            "count": 205,
+                                            "total": 564.7037608690362,
+                                            "count": 18203,
                                             "is_parallel": true,
-                                            "self": 5.8094503130087105,
+                                            "self": 259.6087391550409,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -71,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.01389199400000507,
+                                                            "total": 0.0034653940001589945,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.005428298999504477,
+                                                            "self": 0.001138624001214339,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.008463695000500593,
+                                                                    "total": 0.0023267699989446555,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.008463695000500593
+                                                                    "self": 0.0023267699989446555
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.08793814299951919,
+                                                            "total": 0.048433474999910686,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0008381149991691927,
+                                                            "self": 0.0011167940001541865,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00044880699988425476,
+                                                                    "total": 0.0004689799998232047,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00044880699988425476
+                                                                    "self": 0.0004689799998232047
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.08430419100022846,
+                                                                    "total": 0.04414669200014032,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.08430419100022846
+                                                                    "self": 0.04414669200014032
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0023470300002372824,
+                                                                    "total": 0.0027010089997929754,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00041481400057818973,
+                                                                    "self": 0.0004508740012170165,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0019322159996590926,
+                                                                            "total": 0.002250134998575959,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0019322159996590926
+                                                                            "self": 0.002250134998575959
                                                                         }
                                                                     }
                                                                 }
@@ -121,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 3.6518982899960974,
-                                                    "count": 204,
+                                                    "total": 305.09502171399527,
+                                                    "count": 18202,
                                                     "is_parallel": true,
-                                                    "self": 0.15933613198103558,
+                                                    "self": 14.682019873879653,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 0.0838301130097534,
-                                                            "count": 204,
+                                                            "total": 7.409966176977832,
+                                                            "count": 18202,
                                                             "is_parallel": true,
-                                                            "self": 0.0838301130097534
+                                                            "self": 7.409966176977832
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 2.924155008001435,
-                                                            "count": 204,
+                                                            "total": 239.61788703007096,
+                                                            "count": 18202,
                                                             "is_parallel": true,
-                                                            "self": 2.924155008001435
+                                                            "self": 239.61788703007096
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 0.48457703700387356,
-                                                            "count": 204,
+                                                            "total": 43.38514863306682,
+                                                            "count": 18202,
                                                             "is_parallel": true,
-                                                            "self": 0.10604473899638833,
+                                                            "self": 8.557538232142178,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.3785322980074852,
-                                                                    "count": 2040,
+                                                                    "total": 34.82761040092464,
+                                                                    "count": 182020,
                                                                     "is_parallel": true,
-                                                                    "self": 0.3785322980074852
+                                                                    "self": 34.82761040092464
                                                                 }
                                                             }
                                                         }
@@ -163,9 +309,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 3.1321000278694555e-05,
+                    "total": 0.00014916700001776917,
                     "count": 1,
-                    "self": 3.1321000278694555e-05,
+                    "self": 0.00014916700001776917,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -174,22 +320,36 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 6.112262150948482,
-                                    "count": 13598,
+                                    "total": 556.5169647229022,
+                                    "count": 745308,
                                     "is_parallel": true,
-                                    "self": 0.27250808092503576,
+                                    "self": 17.246539132979706,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 5.839754070023446,
-                                            "count": 13598,
+                                            "total": 312.6194226019261,
+                                            "count": 745308,
                                             "is_parallel": true,
-                                            "self": 5.172752459024196,
+                                            "self": 301.6695909449236,
                                             "children": {
                                                 "RLTrainer._checkpoint": {
-                                                    "total": 0.6670016109992503,
-                                                    "count": 4,
+                                                    "total": 10.949831657002505,
+                                                    "count": 40,
+                                                    "is_parallel": true,
+                                                    "self": 10.949831657002505
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 226.65100298799643,
+                                            "count": 90,
+                                            "is_parallel": true,
+                                            "self": 68.8151287230121,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 157.83587426498434,
+                                                    "count": 4584,
                                                     "is_parallel": true,
-                                                    "self": 0.6670016109992503
+                                                    "self": 157.83587426498434
                                                 }
                                             }
                                         }
@@ -200,14 +360,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.08575392000057036,
+                    "total": 0.08148326100035774,
                     "count": 1,
-                    "self": 0.0011541160001797834,
+                    "self": 0.0008534940006938996,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.08459980400039058,
+                            "total": 0.08062976699966384,
                             "count": 1,
-                            "self": 0.08459980400039058
+                            "self": 0.08062976699966384
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,22 +2,103 @@
     "SnowballTarget": {
         "checkpoints": [
             {
-                "steps": 2200,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-2200.onnx",
-                "reward": 3.6363636363636362,
-                "creation_time": 1728300434.9095323,
+                "steps": 159936,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-159936.onnx",
+                "reward": 25.363636363636363,
+                "creation_time": 1728301927.5924664,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-2200.pt"
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-159936.pt"
+                ]
+            },
+            {
+                "steps": 164992,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-164992.onnx",
+                "reward": 23.5,
+                "creation_time": 1728301942.517483,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-164992.pt"
+                ]
+            },
+            {
+                "steps": 169976,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-169976.onnx",
+                "reward": 25.90909090909091,
+                "creation_time": 1728301955.0906982,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-169976.pt"
+                ]
+            },
+            {
+                "steps": 174952,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-174952.onnx",
+                "reward": 25.454545454545453,
+                "creation_time": 1728301969.32009,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-174952.pt"
+                ]
+            },
+            {
+                "steps": 179992,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-179992.onnx",
+                "reward": 26.545454545454547,
+                "creation_time": 1728301983.2235465,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-179992.pt"
+                ]
+            },
+            {
+                "steps": 184992,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-184992.onnx",
+                "reward": 24.818181818181817,
+                "creation_time": 1728301998.1268618,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-184992.pt"
+                ]
+            },
+            {
+                "steps": 189968,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-189968.onnx",
+                "reward": 25.363636363636363,
+                "creation_time": 1728302012.1121416,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-189968.pt"
+                ]
+            },
+            {
+                "steps": 194944,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-194944.onnx",
+                "reward": 26.181818181818183,
+                "creation_time": 1728302024.8860347,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-194944.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 26.181818181818183,
+                "creation_time": 1728302038.6100218,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 200112,
+                "file_path": "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 26.181818181818183,
+                "creation_time": 1728302038.7214043,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 2200,
-            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 3.6363636363636362,
-            "creation_time": 1728300434.9095323,
+            "steps": 200112,
+            "file_path": "results/SnowballTarget2/SnowballTarget.onnx",
+            "reward": 26.181818181818183,
+            "creation_time": 1728302038.7214043,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-2200.pt"
+                "results/SnowballTarget2/SnowballTarget/SnowballTarget-200112.pt"
             ]
         }
     },