First Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fedccad11a64198517ebb801933ed48792f3f6bcfd5df95a52884e82d44bdfff
+oid sha256:6816feb7837f19506c13217383c701a14e9b58fdacc718c5f65963183c124d00
 size 646532

SnowballTarget/SnowballTarget-149984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a452efce985071d2023b59732ce09c6c2926cf12a2aef50599bd2658ee4c9157
+oid sha256:0cc5a3eb1ba334f226e935b591cbb313770d409c93cd2fc3cd40a5b3968def31
 size 646532

SnowballTarget/SnowballTarget-149984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b017afdcec9592495ecb6afa5bdf557c6f81e6193c518ee994b955543c6f1b2
+oid sha256:e3e574d02fd78b112068689eb719cc1461fa7dbdde4ba03c1e9d11c18b06fb54
 size 3843968

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fedccad11a64198517ebb801933ed48792f3f6bcfd5df95a52884e82d44bdfff
+oid sha256:6816feb7837f19506c13217383c701a14e9b58fdacc718c5f65963183c124d00
 size 646532

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed35d179171e02b5e2a62ae2235c8de336f7c6c5570ace3e41d1d8a7415dd31c
+oid sha256:4f14a0a2bc6c9b2ec8979b207f832a9070854420b3a93221bef3dcdc0518b67f
 size 3843968

SnowballTarget/SnowballTarget-200112.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fedccad11a64198517ebb801933ed48792f3f6bcfd5df95a52884e82d44bdfff
+oid sha256:6816feb7837f19506c13217383c701a14e9b58fdacc718c5f65963183c124d00
 size 646532

SnowballTarget/SnowballTarget-200112.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78d532881f6222dd30dc73091de9ad0ff585d03d7f9e797fdc675429ff0f7cc2
+oid sha256:18ead7107ac23d8a1fca6b214899050315d7e88fee8c1df9ef72e20bb203c3e1
 size 3843968

SnowballTarget/SnowballTarget-49936.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e4d754b724eca5c34765b69e2f3c285b4f9d263b9e25fe9cec5e61f2bda02fc
+oid sha256:a54dc86d8efecb0bbdb9bc2b1f063e8004d12513addf8e23811dfad8b5c38653
 size 646532

SnowballTarget/SnowballTarget-49936.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0b28ff663060972f179d03a378ea56f2faed25a1d57a76f184f54f779239f79
+oid sha256:c42347e3901e83268429570468661a844bbf287b2bbae3ca4380e3300706b0ca
 size 3843968

SnowballTarget/SnowballTarget-99960.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:497e6b47a7feb15a2eb95ea4455b010c3d034237462e41824a2d2dcfce25c3fe
+oid sha256:e516bc100a4cc692fbce3b847451b3d67da8c828b250dea20f78bd8eed4bbe30
 size 646532

SnowballTarget/SnowballTarget-99960.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:436dfe456d95f4306e11fd370c3397390fbadad42475531f8f072a4342e91383
+oid sha256:9f3733636314802d952073dc28b350f087e573a3016766f26984076fba513078
 size 3843968

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78d532881f6222dd30dc73091de9ad0ff585d03d7f9e797fdc675429ff0f7cc2
+oid sha256:18ead7107ac23d8a1fca6b214899050315d7e88fee8c1df9ef72e20bb203c3e1
 size 3843968

SnowballTarget/events.out.tfevents.1680722767.3c41d11ed1b0.1610.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac97d22116286ccb28599a95d45d2c1beb40d122e7115d6916f2f34cc9b346e1
+size 33220

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": 0.96, "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, "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}, "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, "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}, "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

@@ -8,7 +8,7 @@ behaviors:
       learning_rate: 0.0003
       beta: 0.005
       epsilon: 0.2
-      lambd: 0.96
+      lambd: 0.95
       num_epoch: 3
       shared_critic: false
       learning_rate_schedule: linear
@@ -67,7 +67,7 @@ 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:2642:(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  0.078 seconds
+- Completed reload, in  0.081 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: 0.756673 ms
+UnloadTime: 0.812535 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]: 5375 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
@@ -166,22 +169,22 @@ 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 46
     [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]: 5467 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.1 MB
+      Peak Allocated memory 6.7 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 1 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 5467 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.3 MB
+      Peak Allocated memory 17.8 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 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]: 4093 frames, [64.0 KB-128.0 KB]: 1374 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 65.6 KB
+      Peak Allocated memory 67.3 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5467 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]: 5467 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]: 5466 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]: 5467 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]: 5467 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": 1.109220027923584,
+            "min": 1.109220027923584,
+            "max": 2.874509572982788,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 10651.83984375,
+            "min": 10651.83984375,
+            "max": 29437.853515625,
+            "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": 12.509050369262695,
+            "min": 0.4433053135871887,
+            "max": 12.509050369262695,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2439.264892578125,
+            "min": 86.00122833251953,
+            "max": 2506.47802734375,
+            "count": 20
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 20
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 10945.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06941677913881208,
+            "min": 0.06268367462325841,
+            "max": 0.07420617734754285,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.27766711655524834,
+            "min": 0.25073469849303365,
+            "max": 0.35476253323002876,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.20649302524386667,
+            "min": 0.11540351335333623,
+            "max": 0.2885289260569741,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.8259721009754667,
+            "min": 0.46161405341334494,
+            "max": 1.4426446302848706,
+            "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": 25.25,
+            "min": 3.25,
+            "max": 25.25,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1111.0,
+            "min": 143.0,
+            "max": 1349.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 25.25,
+            "min": 3.25,
+            "max": 25.25,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1111.0,
+            "min": 143.0,
+            "max": 1349.0,
+            "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": "1680632345",
+        "start_time_seconds": "1680722766",
         "python_version": "3.9.16 (main, Dec  7 2022, 01:11:51) \n[GCC 9.4.0]",
-        "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": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1680632350"
+        "end_time_seconds": "1680723225"
     },
-    "total": 4.964410488999874,
+    "total": 459.53633219899996,
     "count": 1,
-    "self": 0.8029563559998678,
+    "self": 0.8385480459998575,
     "children": {
         "run_training.setup": {
-            "total": 0.008384949000173947,
+            "total": 0.10955127800002629,
             "count": 1,
-            "self": 0.008384949000173947
+            "self": 0.10955127800002629
         },
         "TrainerController.start_learning": {
-            "total": 4.153069183999833,
+            "total": 458.5882328750001,
             "count": 1,
-            "self": 0.00038638300020465977,
+            "self": 0.5549748029926604,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.9220151989998158,
+                    "total": 3.930294607999997,
                     "count": 1,
-                    "self": 3.9220151989998158
+                    "self": 3.930294607999997
+                },
+                "TrainerController.advance": {
+                    "total": 453.88803937800753,
+                    "count": 18222,
+                    "self": 0.27552384599874813,
+                    "children": {
+                        "env_step": {
+                            "total": 453.6125155320088,
+                            "count": 18222,
+                            "self": 334.7367689289958,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 118.60141212600422,
+                                    "count": 18222,
+                                    "self": 1.6478542400009815,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 116.95355788600324,
+                                            "count": 18222,
+                                            "self": 116.95355788600324
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.2743344770087788,
+                                    "count": 18222,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 457.00839258499406,
+                                            "count": 18222,
+                                            "is_parallel": true,
+                                            "self": 210.83706595399235,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.004812962000016796,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0031248619999360017,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0016881000000807944,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0016881000000807944
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.036083200999996734,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006216170000357124,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.000414060000025529,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.000414060000025529
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.033221355999955904,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.033221355999955904
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0018261679999795888,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00037380800000619274,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.001452359999973396,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.001452359999973396
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 246.1713266310017,
+                                                    "count": 18221,
+                                                    "is_parallel": true,
+                                                    "self": 9.943378263996578,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 5.446890979003456,
+                                                            "count": 18221,
+                                                            "is_parallel": true,
+                                                            "self": 5.446890979003456
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 199.48527966299764,
+                                                            "count": 18221,
+                                                            "is_parallel": true,
+                                                            "self": 199.48527966299764
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 31.29577772500403,
+                                                            "count": 18221,
+                                                            "is_parallel": true,
+                                                            "self": 6.185652642997411,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 25.11012508200662,
+                                                                    "count": 182210,
+                                                                    "is_parallel": true,
+                                                                    "self": 25.11012508200662
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
                 },
                 "trainer_threads": {
-                    "total": 1.8867000108002685e-05,
+                    "total": 0.00018106299989995023,
                     "count": 1,
-                    "self": 1.8867000108002685e-05,
+                    "self": 0.00018106299989995023,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -43,16 +320,38 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 0.0003084939999098424,
-                                    "count": 1,
+                                    "total": 450.6129958280048,
+                                    "count": 399453,
                                     "is_parallel": true,
-                                    "self": 2.7613999918685295e-05,
+                                    "self": 9.727005452037588,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 0.0002808799999911571,
-                                            "count": 1,
+                                            "total": 246.60433654096784,
+                                            "count": 399453,
+                                            "is_parallel": true,
+                                            "self": 245.45083934896786,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 1.1534971919999748,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 1.1534971919999748
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 194.28165383499936,
+                                            "count": 90,
                                             "is_parallel": true,
-                                            "self": 0.0002808799999911571
+                                            "self": 74.4786849539982,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 119.80296888100116,
+                                                    "count": 4587,
+                                                    "is_parallel": true,
+                                                    "self": 119.80296888100116
+                                                }
+                                            }
                                         }
                                     }
                                 }
@@ -61,14 +360,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.23064873499970417,
+                    "total": 0.2147430229999827,
                     "count": 1,
-                    "self": 0.0013565559997914534,
+                    "self": 0.0011691629999859288,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.22929217899991272,
+                            "total": 0.21357385999999678,
                             "count": 1,
-                            "self": 0.22929217899991272
+                            "self": 0.21357385999999678
                         }
                     }
                 }

run_logs/training_status.json

@@ -4,8 +4,8 @@
             {
                 "steps": 49936,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 14.818181818181818,
-                "creation_time": 1680630943.9891295,
+                "reward": 12.090909090909092,
+                "creation_time": 1680722884.6818304,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
                 ]
@@ -13,8 +13,8 @@
             {
                 "steps": 99960,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 21.818181818181817,
-                "creation_time": 1680631055.286782,
+                "reward": 20.0,
+                "creation_time": 1680722997.3095021,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
                 ]
@@ -22,8 +22,8 @@
             {
                 "steps": 149984,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 24.181818181818183,
-                "creation_time": 1680631163.4043715,
+                "reward": 23.545454545454547,
+                "creation_time": 1680723111.4636688,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
                 ]
@@ -31,8 +31,8 @@
             {
                 "steps": 199984,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 26.363636363636363,
-                "creation_time": 1680631270.8331301,
+                "reward": 24.636363636363637,
+                "creation_time": 1680723224.8729446,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
                 ]
@@ -40,17 +40,8 @@
             {
                 "steps": 200112,
                 "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 26.363636363636363,
-                "creation_time": 1680631270.981086,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
-                ]
-            },
-            {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": null,
-                "creation_time": 1680632349.4084258,
+                "reward": 24.636363636363637,
+                "creation_time": 1680723225.115206,
                 "auxillary_file_paths": [
                     "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
                 ]
@@ -59,8 +50,8 @@
         "final_checkpoint": {
             "steps": 200112,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": null,
-            "creation_time": 1680632349.4084258,
+            "reward": 24.636363636363637,
+            "creation_time": 1680723225.115206,
             "auxillary_file_paths": [
                 "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
             ]