First Push

SnowballTarget.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2b584d0498001ca7470dccd13acb604da81620cf5d52818dce8b61a2c105de0
+size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e82f486d08a1d5484e287ad9dddde1c0c3050e0690087cbd397557241ded04c
+size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7dece237c60745f4ceb81f51de29dd3db80ac9cc1d938fed353fc4583667697b
+size 3850075

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2b584d0498001ca7470dccd13acb604da81620cf5d52818dce8b61a2c105de0
+size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:517dd7940549d0d4ae006db906543270853cd3270b930b40291f503c9deeb057
+size 3850075

SnowballTarget/SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2b584d0498001ca7470dccd13acb604da81620cf5d52818dce8b61a2c105de0
+size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e0a23149cc02f6e3b68a0d684aca6e90d44d55e7b51101a9353280583b859d9
+size 3850075

SnowballTarget/SnowballTarget-49936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d296e4d696513798c56a401b01f4b6832b9ad26c1e5ac5f418123300b727976
+size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c39e77d61e0d046b663c8a68ba3221967bf88656c8567529620056010cb1488
+size 3850000

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bca590c69e280cb6f0016aea2f449dd7c0551f53abc3630a01fc76e7f46a54d
+size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ccddcf8186b04f6ad3cd8a05711739ca55fbaf8917e0a55c285b2f3406582d9
+size 3850000

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:928c9272c088e8dd0a9eeab0c47ed9f632239cff37914a68e166bd0cf34a0261
+size 3849250

SnowballTarget/events.out.tfevents.1736831741.ad4166b57693.16028.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:516e4b080321d3601ae40567edd0d0756f2ed240a04295b31c2908aa51afacf5
+size 100940

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 1000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -40,8 +40,8 @@ behaviors:
     even_checkpoints: false
     max_steps: 200000
     time_horizon: 64
-    summary_freq: 10000
-    threaded: true
+    summary_freq: 1000
+    threaded: false
     self_play: null
     behavioral_cloning: null
 env_settings:
@@ -70,7 +70,7 @@ checkpoint_settings:
   initialize_from: null
   load_model: false
   resume: false
-  force: false
+  force: true
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -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  0.095 seconds
+- Completed reload, in  0.084 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: 0.858359 ms
+UnloadTime: 0.662205 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]: 38 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 5367 frames, [16.0 KB-32.0 KB]: 90 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 40
     [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]: 39 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 5458 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 4.8 MB
+      Peak Allocated memory 6.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 39 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 5458 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]: 35 frames, [64.0 KB-128.0 KB]: 4 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5142 frames, [64.0 KB-128.0 KB]: 316 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 65.6 KB
+      Peak Allocated memory 66.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 39 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5458 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]: 39 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5458 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]: 38 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5457 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]: 39 frames
+      Peak usage frame count: [0-1.0 KB]: 5458 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]: 39 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 5458 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": 0.803484320640564,
+            "min": 0.7628971338272095,
+            "max": 2.8903205394744873,
+            "count": 200
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 565.6529541015625,
+            "min": 537.07958984375,
+            "max": 4298.21630859375,
+            "count": 200
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 199984.0,
+            "min": 960.0,
+            "max": 199984.0,
+            "count": 200
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 199984.0,
+            "min": 960.0,
+            "max": 199984.0,
+            "count": 200
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 13.181304931640625,
+            "min": 0.06443431973457336,
+            "max": 13.206515312194824,
+            "count": 200
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 210.90087890625,
+            "min": 0.9665148258209229,
+            "max": 342.58013916015625,
+            "count": 200
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 200
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 200
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.07686452096437707,
+            "min": 0.0507554501533627,
+            "max": 0.09012304773262027,
+            "count": 90
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.07686452096437707,
+            "min": 0.0507554501533627,
+            "max": 0.09012304773262027,
+            "count": 90
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.20188107180829143,
+            "min": 0.10993161987440259,
+            "max": 0.3576154013474782,
+            "count": 90
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.20188107180829143,
+            "min": 0.10993161987440259,
+            "max": 0.3576154013474782,
+            "count": 90
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 3.1320989560000013e-06,
+            "min": 3.1320989560000013e-06,
+            "max": 0.000296832001056,
+            "count": 90
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 3.1320989560000013e-06,
+            "min": 3.1320989560000013e-06,
+            "max": 0.000296832001056,
+            "count": 90
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.101044,
+            "min": 0.101044,
+            "max": 0.198944,
+            "count": 90
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.101044,
+            "min": 0.101044,
+            "max": 0.198944,
+            "count": 90
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 6.209560000000005e-05,
+            "min": 6.209560000000005e-05,
+            "max": 0.0049473056,
+            "count": 90
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 6.209560000000005e-05,
+            "min": 6.209560000000005e-05,
+            "max": 0.0049473056,
+            "count": 90
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 90
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 2189.0,
+            "min": 2189.0,
+            "max": 2189.0,
+            "count": 90
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 29.0,
+            "min": 3.0,
+            "max": 30.0,
+            "count": 108
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 29.0,
+            "min": 3.0,
+            "max": 296.0,
+            "count": 108
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 29.0,
+            "min": 3.0,
+            "max": 30.0,
+            "count": 108
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 29.0,
+            "min": 3.0,
+            "max": 296.0,
+            "count": 108
+        }
+    },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1736828380",
+        "start_time_seconds": "1736831740",
         "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=SnowballTarget1 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
         "mlagents_version": "1.2.0.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": "1736831304"
+        "end_time_seconds": "1736832172"
     },
-    "total": 2923.657183952,
+    "total": 431.8959257030001,
     "count": 1,
-    "self": 0.42285245399989435,
+    "self": 0.42808311700082413,
     "children": {
         "run_training.setup": {
-            "total": 0.05899757399998862,
+            "total": 0.05584461599983115,
             "count": 1,
-            "self": 0.05899757399998862
+            "self": 0.05584461599983115
         },
         "TrainerController.start_learning": {
-            "total": 2923.1753339240004,
+            "total": 431.41199796999945,
             "count": 1,
-            "self": 0.0036916210005983885,
+            "self": 0.3641833590127135,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 5.62553995799999,
+                    "total": 1.941880212000342,
                     "count": 1,
-                    "self": 5.62553995799999
+                    "self": 1.941880212000342
                 },
                 "TrainerController.advance": {
-                    "total": 2917.5432696589996,
-                    "count": 128,
-                    "self": 0.001650475999667833,
+                    "total": 429.01779893198636,
+                    "count": 18192,
+                    "self": 0.37645742895165313,
                     "children": {
                         "env_step": {
-                            "total": 2917.541619183,
-                            "count": 128,
-                            "self": 2916.2190069139997,
+                            "total": 301.3302726129846,
+                            "count": 18192,
+                            "self": 230.04266327501045,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 1.3210949270003312,
-                                    "count": 128,
-                                    "self": 0.008665538000286688,
+                                    "total": 71.06606058199532,
+                                    "count": 18192,
+                                    "self": 1.2500780270042924,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 1.3124293890000445,
-                                            "count": 128,
-                                            "self": 1.3124293890000445
+                                            "total": 69.81598255499102,
+                                            "count": 18192,
+                                            "self": 69.81598255499102
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.001517341999999644,
-                                    "count": 128,
+                                    "total": 0.22154875597880164,
+                                    "count": 18192,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 8.674463628000069,
-                                            "count": 128,
+                                            "total": 429.78371514798255,
+                                            "count": 18192,
                                             "is_parallel": true,
-                                            "self": 7.248302213000102,
+                                            "self": 228.42536628699145,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -71,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0020915270000045894,
+                                                            "total": 0.002265427000111231,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006271099999253238,
+                                                            "self": 0.000676131000091118,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0014644170000792656,
+                                                                    "total": 0.0015892960000201128,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0014644170000792656
+                                                                    "self": 0.0015892960000201128
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.03501447899998311,
+                                                            "total": 0.03557796499990218,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006033180000599714,
+                                                            "self": 0.0008088620002126845,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0003948199999967983,
+                                                                    "total": 0.00039372099990941933,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003948199999967983
+                                                                    "self": 0.00039372099990941933
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.032124030999966635,
+                                                                    "total": 0.03227820199981579,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.032124030999966635
+                                                                    "self": 0.03227820199981579
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.001892309999959707,
+                                                                    "total": 0.0020971799999642826,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00036987899989071593,
+                                                                    "self": 0.00042500300014580716,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0015224310000689911,
+                                                                            "total": 0.0016721769998184755,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0015224310000689911
+                                                                            "self": 0.0016721769998184755
                                                                         }
                                                                     }
                                                                 }
@@ -121,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1.4261614149999673,
-                                                    "count": 127,
+                                                    "total": 201.3583488609911,
+                                                    "count": 18191,
                                                     "is_parallel": true,
-                                                    "self": 0.06783201600018174,
+                                                    "self": 9.91710704694924,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 0.035818923999897834,
-                                                            "count": 127,
+                                                            "total": 5.416393375051484,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 0.035818923999897834
+                                                            "self": 5.416393375051484
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1.1014211039997122,
-                                                            "count": 127,
+                                                            "total": 153.93211714395966,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 1.1014211039997122
+                                                            "self": 153.93211714395966
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 0.22108937100017556,
-                                                            "count": 127,
+                                                            "total": 32.09273129503072,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 0.040240069999356365,
+                                                            "self": 5.807635553239379,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.1808493010008192,
-                                                                    "count": 1270,
+                                                                    "total": 26.285095741791338,
+                                                                    "count": 181910,
                                                                     "is_parallel": true,
-                                                                    "self": 0.1808493010008192
+                                                                    "self": 26.285095741791338
                                                                 }
                                                             }
                                                         }
@@ -159,31 +305,33 @@
                                     }
                                 }
                             }
-                        }
-                    }
-                },
-                "trainer_threads": {
-                    "total": 3.375100004632259e-05,
-                    "count": 1,
-                    "self": 3.375100004632259e-05,
-                    "children": {
-                        "thread_root": {
-                            "total": 0.0,
-                            "count": 0,
-                            "is_parallel": true,
-                            "self": 0.0,
+                        },
+                        "trainer_advance": {
+                            "total": 127.31106889005014,
+                            "count": 18192,
+                            "self": 0.4472302320777999,
                             "children": {
-                                "trainer_advance": {
-                                    "total": 2.012712784001053,
-                                    "count": 7155,
-                                    "is_parallel": true,
-                                    "self": 0.08729719900270538,
+                                "process_trajectory": {
+                                    "total": 29.12317135297417,
+                                    "count": 18192,
+                                    "self": 28.60563932797413,
                                     "children": {
-                                        "process_trajectory": {
-                                            "total": 1.9254155849983476,
-                                            "count": 7155,
-                                            "is_parallel": true,
-                                            "self": 1.9254155849983476
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.5175320250000368,
+                                            "count": 4,
+                                            "self": 0.5175320250000368
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 97.74066730499817,
+                                    "count": 90,
+                                    "self": 40.48459548499795,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 57.256071820000216,
+                                            "count": 4587,
+                                            "self": 57.256071820000216
                                         }
                                     }
                                 }
@@ -191,15 +339,20 @@
                         }
                     }
                 },
+                "trainer_threads": {
+                    "total": 1.0730000212788582e-06,
+                    "count": 1,
+                    "self": 1.0730000212788582e-06
+                },
                 "TrainerController._save_models": {
-                    "total": 0.002798935000100755,
+                    "total": 0.08813439400000789,
                     "count": 1,
-                    "self": 3.2903999908739934e-05,
+                    "self": 0.0011575770004128572,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.002766031000192015,
+                            "total": 0.08697681699959503,
                             "count": 1,
-                            "self": 0.002766031000192015
+                            "self": 0.08697681699959503
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,4 +1,62 @@
 {
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 49936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 14.636363636363637,
+                "creation_time": 1736831852.111799,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                ]
+            },
+            {
+                "steps": 99960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 24.363636363636363,
+                "creation_time": 1736831958.6092737,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                ]
+            },
+            {
+                "steps": 149984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 24.818181818181817,
+                "creation_time": 1736832066.7548122,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 25.636363636363637,
+                "creation_time": 1736832172.0954955,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 200112,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 25.636363636363637,
+                "creation_time": 1736832172.417992,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 200112,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 25.636363636363637,
+            "creation_time": 1736832172.417992,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+            ]
+        }
+    },
     "metadata": {
         "stats_format_version": "0.3.0",
         "mlagents_version": "1.2.0.dev0",