First Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b3171eddf3a582af18f90f6963d5f22a9216b01307ee9f5d7118a5dc23d38eb
+oid sha256:9ca6a39903fb595dfb323a938828eb88c767914ac74998a39f5b0584dff8927d
 size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e938a7e0612f7975f5743b50ca079db060ee4b071aca08f50385ad9476bb5f9
+oid sha256:64ed0f6c23f8d96263bfeee1aaa01ea2ae2d18805eaadd6ff2d9ec50a845d5de
 size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a7e509614d0e5f71a14bfb444d7f700b9ce4a510304e92e6be61692920c0316
+oid sha256:e9e242645331312e1b0a25c1298934bf6525d8f504d634c8c9d58fa5298a7826
 size 3850075

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b3171eddf3a582af18f90f6963d5f22a9216b01307ee9f5d7118a5dc23d38eb
+oid sha256:9ca6a39903fb595dfb323a938828eb88c767914ac74998a39f5b0584dff8927d
 size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7d75f3470c32d91da151eacc3e014ffa7ed9e9403aaeaa308a5d12d1ff687e0
+oid sha256:0fc03c78e6db90a3a750d4171d59c119a8560fc77b4e4aadf321abfa027f4c19
 size 3850075

SnowballTarget/SnowballTarget-200112.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b3171eddf3a582af18f90f6963d5f22a9216b01307ee9f5d7118a5dc23d38eb
+oid sha256:9ca6a39903fb595dfb323a938828eb88c767914ac74998a39f5b0584dff8927d
 size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9f96c7149a7185feed7244ec7c6463768bdcc97aadf2dfb584fdf16f784697e
+oid sha256:e10f03977f7a7d42236ca4f2153d1d0b6348c15713f8c5d0b40c4f574799a1e0
 size 3850075

SnowballTarget/SnowballTarget-49936.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5411fe59dac1c137c28303df33cb94dad41505b3602a32809d5738059cd2b349
+oid sha256:57d70ca5aed13f65e73a0bc45b27e2898c8426cbd100dcdfec88d63bcd47bb92
 size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfcefaea305bbea75368a14f7a16eac943ca7960cd50ab520bde6987d13408d6
+oid sha256:a1943ff22ad65b7c0e30ea5ed7f98ad44e82e47faf130fcc0bba78229799fef8
 size 3850000

SnowballTarget/SnowballTarget-99960.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c662455f3a5e6c588c2106a6bf62c7386af50d5831640e8afb2ff9a981381671
+oid sha256:cfd73c6361f9012d0df83501dc3d4b5cf7a24738f480f716012181587ede88d1
 size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68b9fa8651bacae14702e1b4dba314e7095b63f579a6515815b34f58f4cc43db
+oid sha256:cd1fe8cb2951c3b79c87397d1ba7027211035a6c795b6006be5387ebd24b891f
 size 3850000

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db19a729362efd7e25a78755e42a76dc11cb35731f2102098872129e5fdf666f
+oid sha256:995bd12a19b44b6b879bf09969e329284ed63bc98bd804b61f0fef036c6ead12
 size 3849250

SnowballTarget/events.out.tfevents.1720549044.48a78e3a746c.3562.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84f4894327f6c6871a0a99072856c3ea7881d2f28ad7c044065a1042e278e20e
+size 23668

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

configuration.yaml

@@ -69,7 +69,7 @@ checkpoint_settings:
   run_id: SnowballTarget1
   initialize_from: null
   load_model: false
-  resume: true
+  resume: false
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -2,6 +2,9 @@ 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
@@ -31,7 +34,7 @@ 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  0.097 seconds
+- Completed reload, in  0.086 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -42,7 +45,7 @@ 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: 0.788434 ms
+UnloadTime: 0.721940 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -50,7 +53,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [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
@@ -78,7 +81,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 0]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 2.8 KB
+      Peak Allocated Bytes 3.6 KB
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 10]
       Initial Block Size 32.0 KB
@@ -166,19 +169,19 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 2
+  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]: 1 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 4.8 MB
+      Peak Allocated memory 6.9 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 1 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
@@ -195,7 +198,7 @@ Memory Statistics:
   Overflow Count (full) 0
 [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
   Initial Block Size 2.0 MB
-  Used Block Count 1
+  Used Block Count 2
   Overflow Count (too large) 0
   Overflow Count (full) 0
 [ALLOC_TEMP_JOB_ASYNC (Background)]
@@ -210,13 +213,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 4971 frames, [64.0 KB-128.0 KB]: 490 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]: 1 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
@@ -228,13 +231,13 @@ 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]: 1 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 0.5 MB
+      Peak Allocated memory 0.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [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
@@ -246,13 +249,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 1 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]: 1 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

@@ -1,40 +1,317 @@
 {
     "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 0.8551608324050903,
+            "min": 0.8551608324050903,
+            "max": 2.863596200942993,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 8165.07568359375,
+            "min": 8165.07568359375,
+            "max": 29326.087890625,
+            "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": 12.908926963806152,
+            "min": 0.34415456652641296,
+            "max": 12.908926963806152,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2517.24072265625,
+            "min": 66.76598358154297,
+            "max": 2609.585205078125,
+            "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": 0.06376970518841499,
+            "min": 0.061386327852754705,
+            "max": 0.07624879626660808,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.25507882075365995,
+            "min": 0.24554531141101882,
+            "max": 0.36629197873316666,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.1981519541027499,
+            "min": 0.11478586280010822,
+            "max": 0.27956054391814217,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.7926078164109996,
+            "min": 0.4591434512004329,
+            "max": 1.3978027195907108,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 8.082097306000005e-06,
+            "min": 8.082097306000005e-06,
+            "max": 0.000291882002706,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 3.232838922400002e-05,
+            "min": 3.232838922400002e-05,
+            "max": 0.00138516003828,
+            "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": 25.272727272727273,
+            "min": 3.2954545454545454,
+            "max": 25.436363636363637,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1112.0,
+            "min": 145.0,
+            "max": 1399.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 25.272727272727273,
+            "min": 3.2954545454545454,
+            "max": 25.436363636363637,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1112.0,
+            "min": 145.0,
+            "max": 1399.0,
+            "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": "1720464072",
+        "start_time_seconds": "1720549044",
         "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 --resume",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
         "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": "1720464075"
+        "end_time_seconds": "1720549507"
     },
-    "total": 3.440325830999882,
+    "total": 463.87291561000006,
     "count": 1,
-    "self": 0.5437792239999908,
+    "self": 0.6577600130000292,
     "children": {
         "run_training.setup": {
-            "total": 0.0621576130001813,
+            "total": 0.05525936300000467,
             "count": 1,
-            "self": 0.0621576130001813
+            "self": 0.05525936300000467
         },
         "TrainerController.start_learning": {
-            "total": 2.83438899399971,
+            "total": 463.15989623400003,
             "count": 1,
-            "self": 0.0002903419999711332,
+            "self": 0.591940387005593,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.506095942999764,
+                    "total": 2.2275597830000606,
                     "count": 1,
-                    "self": 2.506095942999764
+                    "self": 2.2275597830000606
+                },
+                "TrainerController.advance": {
+                    "total": 460.19576808799457,
+                    "count": 18201,
+                    "self": 0.27721076700152025,
+                    "children": {
+                        "env_step": {
+                            "total": 459.91855732099305,
+                            "count": 18201,
+                            "self": 298.7527347889735,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 160.871258721005,
+                                    "count": 18201,
+                                    "self": 1.5264102020114478,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 159.34484851899356,
+                                            "count": 18201,
+                                            "self": 159.34484851899356
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.294563811014541,
+                                    "count": 18201,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 461.90253251699903,
+                                            "count": 18201,
+                                            "is_parallel": true,
+                                            "self": 232.57437778398844,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0033642420000887796,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0008879160001242781,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0024763259999645015,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0024763259999645015
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.0678634810000176,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006678050001482916,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0004337629999326964,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004337629999326964
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.06455843199989886,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.06455843199989886
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0022034810000377547,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00046058200018705975,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.001742898999850695,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.001742898999850695
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 229.3281547330106,
+                                                    "count": 18200,
+                                                    "is_parallel": true,
+                                                    "self": 10.380060784023271,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 5.5578206519980995,
+                                                            "count": 18200,
+                                                            "is_parallel": true,
+                                                            "self": 5.5578206519980995
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 178.67443159098661,
+                                                            "count": 18200,
+                                                            "is_parallel": true,
+                                                            "self": 178.67443159098661
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 34.71584170600261,
+                                                            "count": 18200,
+                                                            "is_parallel": true,
+                                                            "self": 6.561069892036471,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 28.154771813966136,
+                                                                    "count": 182000,
+                                                                    "is_parallel": true,
+                                                                    "self": 28.154771813966136
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
                 },
                 "trainer_threads": {
-                    "total": 2.073499990729033e-05,
+                    "total": 0.00010808799993355933,
                     "count": 1,
-                    "self": 2.073499990729033e-05,
+                    "self": 0.00010808799993355933,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -43,16 +320,38 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 0.0002479559998391778,
-                                    "count": 1,
+                                    "total": 454.42512175699574,
+                                    "count": 690549,
                                     "is_parallel": true,
-                                    "self": 4.445099966687849e-05,
+                                    "self": 14.508595830963486,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 0.00020350500017229933,
-                                            "count": 1,
+                                            "total": 251.96563543203285,
+                                            "count": 690549,
+                                            "is_parallel": true,
+                                            "self": 251.1412543010331,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 0.8243811309997682,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 0.8243811309997682
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 187.9508904939994,
+                                            "count": 90,
                                             "is_parallel": true,
-                                            "self": 0.00020350500017229933
+                                            "self": 57.741633900997385,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 130.209256593002,
+                                                    "count": 4587,
+                                                    "is_parallel": true,
+                                                    "self": 130.209256593002
+                                                }
+                                            }
                                         }
                                     }
                                 }
@@ -61,14 +360,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.32798197400006757,
+                    "total": 0.14451988799987703,
                     "count": 1,
-                    "self": 0.001384298999710154,
+                    "self": 0.004861969999865323,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.3265976750003574,
+                            "total": 0.1396579180000117,
                             "count": 1,
-                            "self": 0.3265976750003574
+                            "self": 0.1396579180000117
                         }
                     }
                 }

run_logs/training_status.json

@@ -4,8 +4,8 @@
             {
                 "steps": 49936,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 12.909090909090908,
-                "creation_time": 1720462409.4250655,
+                "reward": 13.272727272727273,
+                "creation_time": 1720549163.8437276,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
                 ]
@@ -13,8 +13,8 @@
             {
                 "steps": 99960,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 19.727272727272727,
-                "creation_time": 1720462548.9147902,
+                "reward": 20.727272727272727,
+                "creation_time": 1720549277.6685998,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
                 ]
@@ -22,8 +22,8 @@
             {
                 "steps": 149984,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 22.454545454545453,
-                "creation_time": 1720462688.3098125,
+                "reward": 24.181818181818183,
+                "creation_time": 1720549392.941421,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
                 ]
@@ -31,8 +31,8 @@
             {
                 "steps": 199984,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 23.90909090909091,
-                "creation_time": 1720462826.4944744,
+                "reward": 25.363636363636363,
+                "creation_time": 1720549507.1207333,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
                 ]
@@ -40,26 +40,8 @@
             {
                 "steps": 200112,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 23.90909090909091,
-                "creation_time": 1720462826.645128,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
-                ]
-            },
-            {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": null,
-                "creation_time": 1720463993.4063628,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
-                ]
-            },
-            {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": null,
-                "creation_time": 1720464074.9801645,
+                "reward": 25.363636363636363,
+                "creation_time": 1720549507.2984257,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
                 ]
@@ -68,8 +50,8 @@
         "final_checkpoint": {
             "steps": 200112,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": null,
-            "creation_time": 1720464074.9801645,
+            "reward": 25.363636363636363,
+            "creation_time": 1720549507.2984257,
             "auxillary_file_paths": [
                 "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
             ]