First Push

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f0f08e5962733258ae698e73c3ce962f8c6f55605aa8b3e1583ad71bb421f83
-size 649740
+oid sha256:e49cf5bf3c2176a0bfe83d2cff4db51b0500b73566fb2a6e2a01da4e639a06be
+size 650646

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d610cd2f23660255b33df6ac0e2879be48b99f7df70ef9a60af83135031a38e0
+size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24b08158dc98e8a9706ea09859402e3e37b6f1a3fb717cb9f5917bc711b8ff29
+size 3850075

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e49cf5bf3c2176a0bfe83d2cff4db51b0500b73566fb2a6e2a01da4e639a06be
+size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4a99ba735a392a03eff5fdd1ac8008c3cdad3fa8092c6f0158edc02ba4efba9
+size 3850075

SnowballTarget/SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e49cf5bf3c2176a0bfe83d2cff4db51b0500b73566fb2a6e2a01da4e639a06be
+size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a05619b60ea19376c508f203f23d129ee18c0fd3dde4491d1cfc1774404aecd7
+size 3850075

SnowballTarget/SnowballTarget-49936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dbce129ed69f908eae3267df7fe80d53298ef6926dd6125cfc95d0c57764401
+size 650646

SnowballTarget/SnowballTarget-49936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:780d30451bbfe084700e0fa1ba08cf0e2a31aaa42738322ec9c0b086ec8d9fc2
+size 3850000

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2154a77823578f5f865044d693f0a310b692160ea0bd987869c9ba0da64ae0c
+size 650646

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8009add0e2e29f82b9282a3b994d227b76c54b61aa85cc24afc51d68b695b64
+size 3850000

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a39e79cc42b25b0cf5e93ea23b186cd256dc2d70f6dd2c271253cc128c604523
-size 1285986
+oid sha256:1cc47aaca2f34015412666e5a3707a87c6a7d5082b85fa9d7ef666a3a3852ee1
+size 3849250

SnowballTarget/events.out.tfevents.1743636728.d2d82e6df4b4.2647.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0d968635a0218e0470a3a5261a345ff9509a2ba5aa9ed140252604a71ce1ad9
+size 23397

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": 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": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -41,7 +41,7 @@ behaviors:
     max_steps: 200000
     time_horizon: 64
     summary_freq: 10000
-    threaded: true
+    threaded: false
     self_play: null
     behavioral_cloning: null
 env_settings:
@@ -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  0.086 seconds
+- Completed reload, in  0.094 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)
@@ -42,15 +45,15 @@ 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: 0.745223 ms
+UnloadTime: 0.742711 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 6 worker threads for Enlighten.
+Setting up 1 worker threads for Enlighten.
 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
@@ -70,10 +73,10 @@ Memory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 6]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 0]
       Initial Block Size 256.0 KB
@@ -85,16 +88,6 @@ Memory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
-      Initial Block Size 32.0 KB
-      Current Block Size 32.0 KB
-      Peak Allocated Bytes 0 B
-      Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 5]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
-      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
@@ -105,22 +98,12 @@ Memory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 4]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
-      Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 3]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
-      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_EnlightenWorker] x 6
+    [ALLOC_TEMP_EnlightenWorker]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
@@ -145,7 +128,7 @@ Memory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 11
+    [ALLOC_TEMP_AssetGarbageCollectorHelper]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
@@ -155,51 +138,21 @@ Memory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 9]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
-      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 13]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 8]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
-      Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 7]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
-      Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 1]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
-      Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 2]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
-      Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 3]
+    [ALLOC_TEMP_Background Job.Worker 11]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 11]
+    [ALLOC_TEMP_Background Job.Worker 3]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 10]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 3.6 KB
-      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 0]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
@@ -216,22 +169,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 35
+  Peak main deferred allocation count 44
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 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 5.2 MB
+      Peak Allocated memory 6.5 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 17.4 MB
+      Peak Allocated memory 17.9 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -260,13 +213,13 @@ 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]: 32 frames, [64.0 KB-128.0 KB]: 7 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5086 frames, [64.0 KB-128.0 KB]: 372 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
@@ -278,13 +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]: 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
@@ -296,13 +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]: 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": 0.8009851574897766,
+            "min": 0.7911959290504456,
+            "max": 2.868342876434326,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 7612.56298828125,
+            "min": 7612.56298828125,
+            "max": 29280.04296875,
+            "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": 13.194398880004883,
+            "min": 0.23562657833099365,
+            "max": 13.194398880004883,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2572.90771484375,
+            "min": 45.71155548095703,
+            "max": 2680.05322265625,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06759628342400652,
+            "min": 0.06139321122495234,
+            "max": 0.07208733402756694,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.27038513369602607,
+            "min": 0.24557284489980935,
+            "max": 0.3604366701378347,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.18899611957079054,
+            "min": 0.10983796067896537,
+            "max": 0.2920287071782,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.7559844782831622,
+            "min": 0.4393518427158615,
+            "max": 1.455590943203253,
+            "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.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.Environment.CumulativeReward.mean": {
+            "value": 25.568181818181817,
+            "min": 3.090909090909091,
+            "max": 26.054545454545455,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1125.0,
+            "min": 136.0,
+            "max": 1433.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 25.568181818181817,
+            "min": 3.090909090909091,
+            "max": 26.054545454545455,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1125.0,
+            "min": 136.0,
+            "max": 1433.0,
+            "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": "1743636042",
+        "start_time_seconds": "1743636727",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
-        "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": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.6.0+cu124",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1743636068"
+        "end_time_seconds": "1743637211"
     },
-    "total": 26.480345657999806,
+    "total": 484.37061789099994,
     "count": 1,
-    "self": 0.21004142999981923,
+    "self": 0.4877409739998484,
     "children": {
         "run_training.setup": {
-            "total": 0.02063847999988866,
+            "total": 0.024044658999969215,
             "count": 1,
-            "self": 0.02063847999988866
+            "self": 0.024044658999969215
         },
         "TrainerController.start_learning": {
-            "total": 26.249665748000098,
+            "total": 483.8588322580001,
             "count": 1,
-            "self": 0.0035266950026198174,
+            "self": 0.499780778994932,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 1.9647517490002429,
+                    "total": 3.184274797999933,
                     "count": 1,
-                    "self": 1.9647517490002429
+                    "self": 3.184274797999933
                 },
                 "TrainerController.advance": {
-                    "total": 24.170334299997194,
-                    "count": 128,
-                    "self": 0.0015293359983843402,
+                    "total": 480.08115016900535,
+                    "count": 18192,
+                    "self": 0.49087671700795,
                     "children": {
                         "env_step": {
-                            "total": 24.16880496399881,
-                            "count": 128,
-                            "self": 23.485055854996972,
+                            "total": 344.34769059500195,
+                            "count": 18192,
+                            "self": 262.8020598280134,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 0.6823183159999644,
-                                    "count": 128,
-                                    "self": 0.008546036998268391,
+                                    "total": 81.25449458100422,
+                                    "count": 18192,
+                                    "self": 1.5049460169964277,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 0.673772279001696,
-                                            "count": 128,
-                                            "self": 0.673772279001696
+                                            "total": 79.7495485640078,
+                                            "count": 18192,
+                                            "self": 79.7495485640078
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.0014307930018730985,
-                                    "count": 128,
+                                    "total": 0.2911361859843282,
+                                    "count": 18192,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 4.204845838000892,
-                                            "count": 128,
+                                            "total": 482.03626411100674,
+                                            "count": 18192,
                                             "is_parallel": true,
-                                            "self": 2.879864850001013,
+                                            "self": 252.39714678500968,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -71,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.002128887999788276,
+                                                            "total": 0.005414937999944414,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006583910003428173,
+                                                            "self": 0.003874387999871942,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0014704969994454586,
+                                                                    "total": 0.0015405500000724714,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0014704969994454586
+                                                                    "self": 0.0015405500000724714
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.02771076900035041,
+                                                            "total": 0.03679908699996304,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005893530001230829,
+                                                            "self": 0.00059688399994684,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00024532099996577017,
+                                                                    "total": 0.0004415180000023611,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00024532099996577017
+                                                                    "self": 0.0004415180000023611
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.02497667400029968,
+                                                                    "total": 0.033881097000062255,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.02497667400029968
+                                                                    "self": 0.033881097000062255
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.001899420999961876,
+                                                                    "total": 0.0018795879999515819,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003829820002465567,
+                                                                    "self": 0.0003573810001853417,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0015164389997153194,
+                                                                            "total": 0.0015222069997662402,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0015164389997153194
+                                                                            "self": 0.0015222069997662402
                                                                         }
                                                                     }
                                                                 }
@@ -121,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1.3249809879998793,
-                                                    "count": 127,
+                                                    "total": 229.63911732599706,
+                                                    "count": 18191,
                                                     "is_parallel": true,
-                                                    "self": 0.050404099004481395,
+                                                    "self": 10.481617642007791,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 0.027426493998973456,
-                                                            "count": 127,
+                                                            "total": 5.883328894993724,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 0.027426493998973456
+                                                            "self": 5.883328894993724
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1.0771939710002698,
-                                                            "count": 127,
+                                                            "total": 179.36171470899683,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 1.0771939710002698
+                                                            "self": 179.36171470899683
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 0.16995642399615463,
-                                                            "count": 127,
+                                                            "total": 33.91245607999872,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 0.03239160999783053,
+                                                            "self": 6.540239781013042,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.1375648139983241,
-                                                                    "count": 1270,
+                                                                    "total": 27.372216298985677,
+                                                                    "count": 181910,
                                                                     "is_parallel": true,
-                                                                    "self": 0.1375648139983241
+                                                                    "self": 27.372216298985677
                                                                 }
                                                             }
                                                         }
@@ -159,31 +305,33 @@
                                     }
                                 }
                             }
-                        }
-                    }
-                },
-                "trainer_threads": {
-                    "total": 3.581200007829466e-05,
-                    "count": 1,
-                    "self": 3.581200007829466e-05,
-                    "children": {
-                        "thread_root": {
-                            "total": 0.0,
-                            "count": 0,
-                            "is_parallel": true,
-                            "self": 0.0,
+                        },
+                        "trainer_advance": {
+                            "total": 135.24258285699545,
+                            "count": 18192,
+                            "self": 0.6973537779904291,
                             "children": {
-                                "trainer_advance": {
-                                    "total": 1.260735278989614,
-                                    "count": 2939,
-                                    "is_parallel": true,
-                                    "self": 0.024087488002351165,
+                                "process_trajectory": {
+                                    "total": 29.333182844005364,
+                                    "count": 18192,
+                                    "self": 28.700100386005147,
                                     "children": {
-                                        "process_trajectory": {
-                                            "total": 1.2366477909872629,
-                                            "count": 2939,
-                                            "is_parallel": true,
-                                            "self": 1.2366477909872629
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.6330824580002172,
+                                            "count": 4,
+                                            "self": 0.6330824580002172
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 105.21204623499966,
+                                    "count": 90,
+                                    "self": 42.26501281699814,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 62.947033418001524,
+                                            "count": 4587,
+                                            "self": 62.947033418001524
                                         }
                                     }
                                 }
@@ -191,15 +339,20 @@
                         }
                     }
                 },
+                "trainer_threads": {
+                    "total": 1.0159999419556698e-06,
+                    "count": 1,
+                    "self": 1.0159999419556698e-06
+                },
                 "TrainerController._save_models": {
-                    "total": 0.11101719199996296,
+                    "total": 0.09362549599995873,
                     "count": 1,
-                    "self": 0.0011018800000783813,
+                    "self": 0.0009814039999582747,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.10991531199988458,
+                            "total": 0.09264409200000046,
                             "count": 1,
-                            "self": 0.10991531199988458
+                            "self": 0.09264409200000046
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,31 +2,58 @@
     "SnowballTarget": {
         "checkpoints": [
             {
-                "steps": 64,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-64.onnx",
-                "reward": null,
-                "creation_time": 1743636016.1890776,
+                "steps": 49936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 17.09090909090909,
+                "creation_time": 1743636850.951208,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-64.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
                 ]
             },
             {
-                "steps": 128,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-128.onnx",
-                "reward": null,
-                "creation_time": 1743636068.7500796,
+                "steps": 99960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 23.181818181818183,
+                "creation_time": 1743636971.3380795,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-128.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                ]
+            },
+            {
+                "steps": 149984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 25.363636363636363,
+                "creation_time": 1743637090.0843136,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                ]
+            },
+            {
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 25.0,
+                "creation_time": 1743637211.403508,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                ]
+            },
+            {
+                "steps": 200112,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 25.0,
+                "creation_time": 1743637211.5103827,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 128,
+            "steps": 200112,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": null,
-            "creation_time": 1743636068.7500796,
+            "reward": 25.0,
+            "creation_time": 1743637211.5103827,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-128.pt"
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
             ]
         }
     },