.

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:805e29e0dea258fbd8c62872a54af02145490c17f9184fab00b1741ec6db6703
-size 1814028
+oid sha256:739867ba7af7748404f94c816b00d286afa7e11d7cd9f1ebed05fadeb7f12a43
+size 1815958

SnowballTarget/SnowballTarget-149960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55af2d7d6ae2a3f78dad67044b2439c23833600a3eb4666e3a3cdf461e47a554
+size 1815958

SnowballTarget/SnowballTarget-149960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcd077db07ffd06478179c7cdf690360cfedbcf52f0fd854479a36c54deb641e
+size 10820443

SnowballTarget/SnowballTarget-199920.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:592efa674896e88c882d6746192ef76d65899f3eed065ac55fecda7766d66799
+size 1815958

SnowballTarget/SnowballTarget-199920.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6db8bddd751d09abd4249f553f79f76e55a03d73f0f690154c3f01eeee4e2200
+size 10820443

SnowballTarget/SnowballTarget-249936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8924c5496f256cc76f5cce8bf3caa9fef1e23d0dc5b8a1ffeb9cec87749f392
+size 1815958

SnowballTarget/SnowballTarget-249936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e0c6f559fa3ed5d24bdd42b2e817133eea5479e728a06007020df6adaf18f8d
+size 10820443

SnowballTarget/SnowballTarget-299960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:739867ba7af7748404f94c816b00d286afa7e11d7cd9f1ebed05fadeb7f12a43
+size 1815958

SnowballTarget/SnowballTarget-299960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1319ffe0ee9795eae2024ab20b3d0491544ec2d0d82e33181efc1fb239c2397b
+size 10820443

SnowballTarget/SnowballTarget-300104.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:739867ba7af7748404f94c816b00d286afa7e11d7cd9f1ebed05fadeb7f12a43
+size 1815958

SnowballTarget/SnowballTarget-300104.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bb3e089c9c1356722dd5fc36b2b28bca88387f7f5f51d363830049edb3728cc
+size 10820443

SnowballTarget/SnowballTarget-49936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6ce0767b17bc1279f52e7a88f4198ef9df37230bb5286a461701972e12b80af
+size 1815958

SnowballTarget/SnowballTarget-49936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e9da38f5d2984bf5ad6f7d916b95ad52dec7fc9b98f33db7df32c77f857328
+size 10820368

SnowballTarget/SnowballTarget-65208.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54702bcc3faf852f8d2458bb78c1c597e798b64e234cd62fe87c261b012402e0
+size 1815958

SnowballTarget/SnowballTarget-65208.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e663874e57e193a2bdb19cbeecc618cd7a7b89b888f389b79684ca607e5659
+size 10820368

SnowballTarget/SnowballTarget-99976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6e990377f6720a7f221ac05634e39a4c010283a5f91ac29f9ca08568964882b
+size 1815958

SnowballTarget/SnowballTarget-99976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fed0bceb406c744f44ca476dbde64fefc11a99b90589ac3d187afdb05f1186db
+size 10820368

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c621c2632c09f83f09e139e60c0c3c9f0f79fe73e945535d315ae0179bbe6556
-size 3609442
+oid sha256:ae597bb36e897b39e227449638d7353c978ed00c48b77139b6b7b73002ded789
+size 10819618

SnowballTarget/events.out.tfevents.1720249336.c27fe8d53be1.6080.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d46cddf19726e5ce3f477f3a4ad93c50358f2dacd22f7957bbe237877c2a827d
+size 25937

SnowballTarget/events.out.tfevents.1720249498.c27fe8d53be1.6821.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:223f8baa20bbd277f6daa66ae2f5343512fa7fca94648bf02feabc72fdc165ee
+size 27266

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 256, "buffer_size": 10240, "learning_rate": 0.0002, "beta": 0.01, "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": 512, "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": 220000, "time_horizon": 128, "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": 256, "buffer_size": 10240, "learning_rate": 0.0002, "beta": 0.01, "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": 512, "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": 300000, "time_horizon": 128, "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": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -38,7 +38,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 10
     even_checkpoints: false
-    max_steps: 220000
+    max_steps: 300000
     time_horizon: 128
     summary_freq: 10000
     threaded: true
@@ -69,7 +69,7 @@ checkpoint_settings:
   run_id: SnowballTarget1
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
 Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
-Unable to load player prefs
 Initialize engine version: 2021.3.14f1 (eee1884e7226)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c: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  0.091 seconds
+- Completed reload, in  0.090 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: 0.853906 ms
+UnloadTime: 0.659639 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]: 159 frames, [16.0 KB-32.0 KB]: 2 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 6315 frames, [16.0 KB-32.0 KB]: 107 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 36
+  Peak main deferred allocation count 44
     [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]: 162 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 6423 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.2 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]: 162 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 6423 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 17.8 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]: 152 frames, [64.0 KB-128.0 KB]: 10 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5024 frames, [64.0 KB-128.0 KB]: 1399 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 65.6 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]: 162 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 6423 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]: 162 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 6423 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]: 161 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 6422 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]: 162 frames
+      Peak usage frame count: [0-1.0 KB]: 6423 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]: 162 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 6423 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": 1.8118195533752441,
+            "min": 1.8118195533752441,
+            "max": 2.771235704421997,
+            "count": 24
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 17378.97265625,
+            "min": 16125.8203125,
+            "max": 27430.41796875,
+            "count": 24
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 299960.0,
+            "min": 69992.0,
+            "max": 299960.0,
+            "count": 24
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 299960.0,
+            "min": 69992.0,
+            "max": 299960.0,
+            "count": 24
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 8.524247169494629,
+            "min": 1.3393324613571167,
+            "max": 8.524247169494629,
+            "count": 24
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 835.376220703125,
+            "min": 62.94862747192383,
+            "max": 854.62353515625,
+            "count": 24
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 24
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 10945.0,
+            "min": 4378.0,
+            "max": 10945.0,
+            "count": 24
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 19.608695652173914,
+            "min": 7.2727272727272725,
+            "max": 20.5,
+            "count": 24
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 902.0,
+            "min": 160.0,
+            "max": 1069.0,
+            "count": 24
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 19.608695652173914,
+            "min": 7.2727272727272725,
+            "max": 20.5,
+            "count": 24
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 902.0,
+            "min": 160.0,
+            "max": 1069.0,
+            "count": 24
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 24
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 24
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.046152475377773894,
+            "min": 0.045261845252724246,
+            "max": 0.05613040942273709,
+            "count": 21
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.046152475377773894,
+            "min": 0.045261845252724246,
+            "max": 0.05613040942273709,
+            "count": 21
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.2707705969611804,
+            "min": 0.2489233562161052,
+            "max": 0.31760141750176746,
+            "count": 21
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.2707705969611804,
+            "min": 0.2489233562161052,
+            "max": 0.31760141750176746,
+            "count": 21
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 3.056098471999992e-06,
+            "min": 3.056098471999992e-06,
+            "max": 0.00014962669185333328,
+            "count": 21
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 3.056098471999992e-06,
+            "min": 3.056098471999992e-06,
+            "max": 0.00014962669185333328,
+            "count": 21
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10152800000000005,
+            "min": 0.10152800000000005,
+            "max": 0.1748133333333333,
+            "count": 21
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.10152800000000005,
+            "min": 0.10152800000000005,
+            "max": 0.1748133333333333,
+            "count": 21
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.00016264719999999966,
+            "min": 0.00016264719999999966,
+            "max": 0.007483852,
+            "count": 21
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.00016264719999999966,
+            "min": 0.00016264719999999966,
+            "max": 0.007483852,
+            "count": 21
+        }
+    },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1720249254",
+        "start_time_seconds": "1720249497",
         "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 --resume",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.3.0+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1720249270"
+        "end_time_seconds": "1720250049"
     },
-    "total": 16.25279369099985,
+    "total": 552.2202583549999,
     "count": 1,
-    "self": 0.14720840399991175,
+    "self": 0.42978697499984264,
     "children": {
         "run_training.setup": {
-            "total": 0.05964862199994059,
+            "total": 0.05920954599992001,
             "count": 1,
-            "self": 0.05964862199994059
+            "self": 0.05920954599992001
         },
         "TrainerController.start_learning": {
-            "total": 16.045936665,
+            "total": 551.7312618340002,
             "count": 1,
-            "self": 0.01878256399845668,
+            "self": 0.7641373830313114,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.8109563699999853,
+                    "total": 2.0999622650001584,
                     "count": 1,
-                    "self": 2.8109563699999853
+                    "self": 2.0999622650001584
                 },
                 "TrainerController.advance": {
-                    "total": 12.917836443001534,
-                    "count": 540,
-                    "self": 0.008619109001074321,
+                    "total": 548.7307076829686,
+                    "count": 21407,
+                    "self": 0.3434664609551419,
                     "children": {
                         "env_step": {
-                            "total": 12.90921733400046,
-                            "count": 540,
-                            "self": 8.603649299005383,
+                            "total": 548.3872412220135,
+                            "count": 21407,
+                            "self": 357.6078869710309,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 4.296834380997325,
-                                    "count": 540,
-                                    "self": 0.04560909600172636,
+                                    "total": 190.41055164898262,
+                                    "count": 21407,
+                                    "self": 1.8487056709798253,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 4.2512252849955985,
-                                            "count": 540,
-                                            "self": 4.2512252849955985
+                                            "total": 188.5618459780028,
+                                            "count": 21407,
+                                            "self": 188.5618459780028
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.00873365399775139,
-                                    "count": 539,
+                                    "total": 0.36880260199995973,
+                                    "count": 21407,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 15.742622637999375,
-                                            "count": 539,
+                                            "total": 550.1251846769994,
+                                            "count": 21407,
                                             "is_parallel": true,
-                                            "self": 8.727718367001216,
+                                            "self": 269.83681195401164,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -71,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.00549071799991907,
+                                                            "total": 0.0026616340001055505,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0039051780001955194,
+                                                            "self": 0.0008052370003497344,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0015855399997235509,
+                                                                    "total": 0.001856396999755816,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0015855399997235509
+                                                                    "self": 0.001856396999755816
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.06512434399996891,
+                                                            "total": 0.045671846000004734,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006391009999333619,
+                                                            "self": 0.000765755999736939,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0003716569999596686,
+                                                                    "total": 0.000451747000170144,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003716569999596686
+                                                                    "self": 0.000451747000170144
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.06223896100004822,
+                                                                    "total": 0.04220969600009994,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.06223896100004822
+                                                                    "self": 0.04220969600009994
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0018746250000276632,
+                                                                    "total": 0.0022446469999977126,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003390939998553222,
+                                                                    "self": 0.0004208880002352089,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001535531000172341,
+                                                                            "total": 0.0018237589997625037,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001535531000172341
+                                                                            "self": 0.0018237589997625037
                                                                         }
                                                                     }
                                                                 }
@@ -121,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 7.014904270998159,
-                                                    "count": 538,
+                                                    "total": 280.2883727229878,
+                                                    "count": 21406,
                                                     "is_parallel": true,
-                                                    "self": 0.3154182389998823,
+                                                    "self": 12.630060233967242,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 0.1720740619987282,
-                                                            "count": 538,
+                                                            "total": 6.792817600001172,
+                                                            "count": 21406,
                                                             "is_parallel": true,
-                                                            "self": 0.1720740619987282
+                                                            "self": 6.792817600001172
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 5.432349116000751,
-                                                            "count": 538,
+                                                            "total": 218.07006982201506,
+                                                            "count": 21406,
                                                             "is_parallel": true,
-                                                            "self": 5.432349116000751
+                                                            "self": 218.07006982201506
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 1.0950628539987974,
-                                                            "count": 538,
+                                                            "total": 42.79542506700432,
+                                                            "count": 21406,
                                                             "is_parallel": true,
-                                                            "self": 0.21312870899510017,
+                                                            "self": 8.107294056017963,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.8819341450036973,
-                                                                    "count": 5380,
+                                                                    "total": 34.68813101098635,
+                                                                    "count": 214060,
                                                                     "is_parallel": true,
-                                                                    "self": 0.8819341450036973
+                                                                    "self": 34.68813101098635
                                                                 }
                                                             }
                                                         }
@@ -163,9 +309,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 2.2120000039649312e-05,
+                    "total": 0.00023989800001800177,
                     "count": 1,
-                    "self": 2.2120000039649312e-05,
+                    "self": 0.00023989800001800177,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -174,16 +320,38 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 12.58680932998277,
-                                    "count": 38900,
+                                    "total": 539.1018590201095,
+                                    "count": 1085599,
                                     "is_parallel": true,
-                                    "self": 0.7406553219732359,
+                                    "self": 24.56119199611271,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 11.846154008009535,
-                                            "count": 38900,
+                                            "total": 362.60708646899616,
+                                            "count": 1085599,
                                             "is_parallel": true,
-                                            "self": 11.846154008009535
+                                            "self": 361.4931656489964,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 1.1139208199997483,
+                                                    "count": 5,
+                                                    "is_parallel": true,
+                                                    "self": 1.1139208199997483
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 151.93358055500062,
+                                            "count": 21,
+                                            "is_parallel": true,
+                                            "self": 69.69792452899833,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 82.23565602600229,
+                                                    "count": 2640,
+                                                    "is_parallel": true,
+                                                    "self": 82.23565602600229
+                                                }
+                                            }
                                         }
                                     }
                                 }
@@ -192,14 +360,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.29833916799998406,
+                    "total": 0.13621460500007743,
                     "count": 1,
-                    "self": 0.002305101999809267,
+                    "self": 0.0026471169999240374,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.2960340660001748,
+                            "total": 0.1335674880001534,
                             "count": 1,
-                            "self": 0.2960340660001748
+                            "self": 0.1335674880001534
                         }
                     }
                 }

run_logs/training_status.json

@@ -9,15 +9,87 @@
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-5808.pt"
                 ]
+            },
+            {
+                "steps": 49936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 6.636363636363637,
+                "creation_time": 1720249445.0350823,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                ]
+            },
+            {
+                "steps": 65208,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-65208.onnx",
+                "reward": 6.606060606060606,
+                "creation_time": 1720249477.8707228,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-65208.pt"
+                ]
+            },
+            {
+                "steps": 99976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99976.onnx",
+                "reward": 9.1875,
+                "creation_time": 1720249581.9225633,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99976.pt"
+                ]
+            },
+            {
+                "steps": 149960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149960.onnx",
+                "reward": 13.295454545454545,
+                "creation_time": 1720249696.0399718,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149960.pt"
+                ]
+            },
+            {
+                "steps": 199920,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199920.onnx",
+                "reward": 16.5,
+                "creation_time": 1720249815.2746449,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199920.pt"
+                ]
+            },
+            {
+                "steps": 249936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249936.onnx",
+                "reward": 18.51851851851852,
+                "creation_time": 1720249928.8175292,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-249936.pt"
+                ]
+            },
+            {
+                "steps": 299960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299960.onnx",
+                "reward": 19.75,
+                "creation_time": 1720250049.0235999,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-299960.pt"
+                ]
+            },
+            {
+                "steps": 300104,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-300104.onnx",
+                "reward": 19.576923076923077,
+                "creation_time": 1720250049.1946568,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-300104.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 5808,
+            "steps": 300104,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 3.227272727272727,
-            "creation_time": 1720249270.666838,
+            "reward": 19.576923076923077,
+            "creation_time": 1720250049.1946568,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-5808.pt"
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-300104.pt"
             ]
         }
     },