2nd try, time_horizon:32

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1c32fde76ed332669579f2f15a9d53102e5c05c90cea4c8068b0fcc2ee6eee0
+oid sha256:30fa6679f977fc3121fb6e1eb099d9642e5184cc4af7bcd1b5956742f07285cf
 size 650646

SnowballTarget/SnowballTarget-0.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d2ef4154bde9f9318b4b7b8ba0b8192a964a2fbab72df143555fd392b1a6c54
+size 649740

SnowballTarget/SnowballTarget-0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:524df05df06938fcd6dc2066e5101c4346309eb8b0f15f482aeb58d4d8157213
+size 1286148

SnowballTarget/SnowballTarget-14992.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c39566cec41904d1d6119ab764f58e187c88ebec28eab4a8869e7b0580b63fd
-size 650646
+oid sha256:df869a4a05afac0aff6d5552fb1a6fd99845849d9e6a812034930f6c33463e61
+size 649740

SnowballTarget/SnowballTarget-14992.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24a8db276d8af610d472ab9e788bec3e67c5eff8a424435580fe680d0b820813
-size 3850000
+oid sha256:6ccbb223c6090e243c9fdcef3556fc09d76fc64a5ec90a8c826065e4dba16f1e
+size 1286256

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95ca774f103587900dcb1a64d3c77f442a4aaab6175b4d23ea81a1093518dfc9
+size 650646

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d1b742443829522f532bc4a6796de283e7d2a69098ddda5a47aae87937631bc
+size 3850075

SnowballTarget/SnowballTarget-19992.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1c32fde76ed332669579f2f15a9d53102e5c05c90cea4c8068b0fcc2ee6eee0
+oid sha256:dc894cc36d88def47a65ba323c39972aa04ff26a083a940385f121b4aee9c81d
 size 650646

SnowballTarget/SnowballTarget-19992.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:189216a41478186909bc278e92a613b28db100e76d271061e7b53937a28b2c0c
+oid sha256:404081356a1b3eedb881e97b4e75c069fe5ca92fe874f539d9cccdc96108c9ec
 size 3850000

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30fa6679f977fc3121fb6e1eb099d9642e5184cc4af7bcd1b5956742f07285cf
+size 650646

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6892ed87f9e3912a888b5945640700aa7dfd5116d0b16971b0e7619ff89d3068
+size 3850075

SnowballTarget/SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30fa6679f977fc3121fb6e1eb099d9642e5184cc4af7bcd1b5956742f07285cf
+size 650646

SnowballTarget/SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad00da6abfda0e8ec1ffa3bdeb8fb49259f6b47cfed7bdf37454de9d0eee1684
+size 3850075

SnowballTarget/SnowballTarget-20152.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc894cc36d88def47a65ba323c39972aa04ff26a083a940385f121b4aee9c81d
+size 650646

SnowballTarget/SnowballTarget-20152.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d5cd75b7aa96c803d545889099c4e7b447446dd382cfe371c0208d9be3f7038
+size 3850000

SnowballTarget/SnowballTarget-2112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c53634711009c16ccfe496c5c490de28f2e708909413f103482fb3d1033990b
+size 649740

SnowballTarget/SnowballTarget-2112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88fb9269075a80d2a4a9d071518c0a0224fc63dcec0b2befc39454fd3433a68a
+size 3849925

SnowballTarget/SnowballTarget-32.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55211a1ce4138e503d9d68b39683f54232b9e9b4a561652a6dd2008257553a66
+size 16709

SnowballTarget/SnowballTarget-4976.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd36390b902bdc4515271b330e9153b7358cd7e41887c8a0e8582f0631e7f8af
-size 650646
+oid sha256:df869a4a05afac0aff6d5552fb1a6fd99845849d9e6a812034930f6c33463e61
+size 649740

SnowballTarget/SnowballTarget-4976.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edae9f956ee3b826de8d0fa9cde0b416b8d5fa90c007d5a8f4ebddd88f0b32f2
-size 3849925
+oid sha256:fee3796d485b561097cd240d4e2dd84c5c104eddd89aa65edfb580b9b0c65649
+size 1286229

SnowballTarget/SnowballTarget-49968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68c1b3851911dfb4bc8c6aafd35e5d4a1d84dcb90a73f2f41d0332013f3f64b2
+size 650646

SnowballTarget/SnowballTarget-49968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bce5ed9940ef2e91e0409fde85ec329727d912f3a6b1be5c36e936d30e978562
+size 3850000

SnowballTarget/SnowballTarget-9984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df869a4a05afac0aff6d5552fb1a6fd99845849d9e6a812034930f6c33463e61
+size 649740

SnowballTarget/SnowballTarget-9984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eaee9fb634e3330cfd7194c4df483e7209e495119638e4c380a9e283ef60af7
+size 1286229

SnowballTarget/SnowballTarget-99992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69cdcca1c801127ee5ac2cd36ff3afcf2ca7bad3cf83727a94d8163b0d05b93f
+size 650646

SnowballTarget/SnowballTarget-99992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e0087d78a7065083cd911d9304a1cd27d8e4f93786af1f088d2d87ac70f0ae5
+size 3850000

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:489687a871bba64a53d175e73cc61932a408a42fbcf1a23ba319dde699593c5d
+oid sha256:d28a4be2746d850ec4c5a76e09689ea822adcca57973ee4b798ff870c0219c87
 size 3849250

SnowballTarget/events.out.tfevents.1739015401.17d192993805.21871.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26e4fa8b996f7d4ceb6416876d37d3fc5619ddac88a02ec75c5fed5255d09b69
+size 28090

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": 5000, "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": 20000, "time_horizon": 64, "summary_freq": 1000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": 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": 32, "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": "my_run_id", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -14,7 +14,7 @@ behaviors:
       learning_rate_schedule: linear
       beta_schedule: linear
       epsilon_schedule: linear
-    checkpoint_interval: 5000
+    checkpoint_interval: 50000
     network_settings:
       normalize: false
       hidden_units: 256
@@ -38,9 +38,9 @@ behaviors:
     init_path: null
     keep_checkpoints: 10
     even_checkpoints: false
-    max_steps: 20000
-    time_horizon: 64
-    summary_freq: 1000
+    max_steps: 200000
+    time_horizon: 32
+    summary_freq: 10000
     threaded: false
     self_play: null
     behavioral_cloning: null
@@ -66,11 +66,11 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: SnowballTarget1
+  run_id: my_run_id
   initialize_from: null
   load_model: false
   resume: false
-  force: false
+  force: true
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
 Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
-Unable to load player prefs
 Initialize engine version: 2021.3.14f1 (eee1884e7226)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.088 seconds
+- Completed reload, in  0.087 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -45,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.733454 ms
+UnloadTime: 0.690815 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -53,7 +50,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 550 frames, [16.0 KB-32.0 KB]: 9 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 5367 frames, [16.0 KB-32.0 KB]: 90 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -169,19 +166,19 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 32
+  Peak main deferred allocation count 40
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 560 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 5.5 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]: 560 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 17.7 MB
@@ -213,13 +210,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 526 frames, [64.0 KB-128.0 KB]: 34 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 4497 frames, [64.0 KB-128.0 KB]: 961 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 66.0 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]: 560 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5458 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -231,13 +228,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 560 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]: 559 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5457 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 MB
@@ -249,13 +246,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 560 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]: 560 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

@@ -2,213 +2,213 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 2.779792547225952,
-            "min": 2.761918306350708,
-            "max": 2.890334129333496,
+            "value": 0.9985322952270508,
+            "min": 0.992946207523346,
+            "max": 2.8741352558135986,
             "count": 20
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 4158.56982421875,
-            "min": 1944.3905029296875,
-            "max": 4300.69482421875,
+            "value": 9841.5341796875,
+            "min": 9841.5341796875,
+            "max": 29339.173828125,
             "count": 20
         },
         "SnowballTarget.Step.mean": {
-            "value": 19992.0,
-            "min": 960.0,
-            "max": 19992.0,
+            "value": 199984.0,
+            "min": 9984.0,
+            "max": 199984.0,
             "count": 20
         },
         "SnowballTarget.Step.sum": {
-            "value": 19992.0,
-            "min": 960.0,
-            "max": 19992.0,
+            "value": 199984.0,
+            "min": 9984.0,
+            "max": 199984.0,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 1.767405390739441,
-            "min": -0.04289287328720093,
-            "max": 1.767405390739441,
+            "value": 12.99207592010498,
+            "min": 0.25616219639778137,
+            "max": 12.99207592010498,
             "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 45.95254135131836,
-            "min": -0.6862859725952148,
-            "max": 45.95254135131836,
-            "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,
+            "value": 4495.25830078125,
+            "min": 88.37596130371094,
+            "max": 4541.1962890625,
             "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.0724283336934533,
-            "min": 0.062277302249533345,
-            "max": 0.08031833225929101,
-            "count": 9
+            "value": 0.06311576881682199,
+            "min": 0.06182950255141466,
+            "max": 0.07774278132423848,
+            "count": 20
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.0724283336934533,
-            "min": 0.062277302249533345,
-            "max": 0.08031833225929101,
-            "count": 9
+            "value": 0.25246307526728795,
+            "min": 0.25246307526728795,
+            "max": 0.36562895962817815,
+            "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.19563980137600617,
-            "min": 0.10465029836632311,
-            "max": 0.2649126134666742,
-            "count": 9
+            "value": 0.19458738341927528,
+            "min": 0.0990260931327665,
+            "max": 0.26105213588943665,
+            "count": 20
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.19563980137600617,
-            "min": 0.10465029836632311,
-            "max": 0.2649126134666742,
-            "count": 9
+            "value": 0.7783495336771011,
+            "min": 0.396104372531066,
+            "max": 1.2331008157309364,
+            "count": 20
         },
         "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 4.320098559999991e-06,
-            "min": 4.320098559999991e-06,
-            "max": 0.00026832001056,
-            "count": 9
+            "value": 8.082097306000005e-06,
+            "min": 8.082097306000005e-06,
+            "max": 0.000291882002706,
+            "count": 20
         },
         "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 4.320098559999991e-06,
-            "min": 4.320098559999991e-06,
-            "max": 0.00026832001056,
-            "count": 9
+            "value": 3.232838922400002e-05,
+            "min": 3.232838922400002e-05,
+            "max": 0.00138516003828,
+            "count": 20
         },
         "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10144,
-            "min": 0.10144,
-            "max": 0.18944000000000003,
-            "count": 9
+            "value": 0.10269400000000001,
+            "min": 0.10269400000000001,
+            "max": 0.19729400000000002,
+            "count": 20
         },
         "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.10144,
-            "min": 0.10144,
-            "max": 0.18944000000000003,
-            "count": 9
+            "value": 0.41077600000000003,
+            "min": 0.41077600000000003,
+            "max": 0.96172,
+            "count": 20
         },
         "SnowballTarget.Policy.Beta.mean": {
-            "value": 8.185599999999986e-05,
-            "min": 8.185599999999986e-05,
-            "max": 0.0044730559999999996,
-            "count": 9
+            "value": 0.0001444306000000001,
+            "min": 0.0001444306000000001,
+            "max": 0.0048649706,
+            "count": 20
         },
         "SnowballTarget.Policy.Beta.sum": {
-            "value": 8.185599999999986e-05,
-            "min": 8.185599999999986e-05,
-            "max": 0.0044730559999999996,
-            "count": 9
+            "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": 9
+            "count": 20
         },
         "SnowballTarget.Environment.EpisodeLength.sum": {
-            "value": 2189.0,
-            "min": 2189.0,
-            "max": 2189.0,
-            "count": 9
+            "value": 8756.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 5.2727272727272725,
-            "min": 3.0,
-            "max": 6.7272727272727275,
-            "count": 10
+            "value": 25.272727272727273,
+            "min": 3.2954545454545454,
+            "max": 25.836363636363636,
+            "count": 20
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 58.0,
-            "min": 6.0,
-            "max": 74.0,
-            "count": 10
+            "value": 1112.0,
+            "min": 145.0,
+            "max": 1421.0,
+            "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 5.2727272727272725,
-            "min": 3.0,
-            "max": 6.7272727272727275,
-            "count": 10
+            "value": 25.272727272727273,
+            "min": 3.2954545454545454,
+            "max": 25.836363636363636,
+            "count": 20
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 58.0,
-            "min": 6.0,
-            "max": 74.0,
-            "count": 10
+            "value": 1112.0,
+            "min": 145.0,
+            "max": 1421.0,
+            "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": "1739012544",
+        "start_time_seconds": "1739015401",
         "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",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=my_run_id --no-graphics --force",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.6.0+cu124",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1739012593"
+        "end_time_seconds": "1739015864"
     },
-    "total": 49.738244314999974,
+    "total": 463.45598870899994,
     "count": 1,
-    "self": 0.4364974039999652,
+    "self": 0.4250834380000015,
     "children": {
         "run_training.setup": {
-            "total": 0.024031331000060163,
+            "total": 0.0212474990003102,
             "count": 1,
-            "self": 0.024031331000060163
+            "self": 0.0212474990003102
         },
         "TrainerController.start_learning": {
-            "total": 49.27771557999995,
+            "total": 463.0096577719996,
             "count": 1,
-            "self": 0.03558147299463599,
+            "self": 0.3859600709429287,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.360511007000241,
+                    "total": 1.9376640410000618,
                     "count": 1,
-                    "self": 3.360511007000241
+                    "self": 1.9376640410000618
                 },
                 "TrainerController.advance": {
-                    "total": 45.79124828100521,
-                    "count": 1864,
-                    "self": 0.03648173899682661,
+                    "total": 460.59248971305533,
+                    "count": 18192,
+                    "self": 0.4063884110564686,
                     "children": {
                         "env_step": {
-                            "total": 32.39992949400266,
-                            "count": 1864,
-                            "self": 24.456847431008555,
+                            "total": 322.5626136260171,
+                            "count": 18192,
+                            "self": 245.0801933370194,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 7.921570120992328,
-                                    "count": 1864,
-                                    "self": 0.1358422439975584,
+                                    "total": 77.24882868398163,
+                                    "count": 18192,
+                                    "self": 1.3689781150214912,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 7.78572787699477,
-                                            "count": 1864,
-                                            "self": 7.78572787699477
+                                            "total": 75.87985056896014,
+                                            "count": 18192,
+                                            "self": 75.87985056896014
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.02151194200177997,
-                                    "count": 1864,
+                                    "total": 0.23359160501604492,
+                                    "count": 18192,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 48.90124615599325,
-                                            "count": 1864,
+                                            "total": 461.4384178079654,
+                                            "count": 18192,
                                             "is_parallel": true,
-                                            "self": 27.460323322988643,
+                                            "self": 246.82315045796713,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.005205362000197056,
+                                                            "total": 0.002171744000406761,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.003562742999292823,
+                                                            "self": 0.0006821830020271591,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.001642619000904233,
+                                                                    "total": 0.001489560998379602,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.001642619000904233
+                                                                    "self": 0.001489560998379602
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.03970961899995018,
+                                                            "total": 0.034984853000423755,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006061809999664547,
+                                                            "self": 0.0005909100000280887,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00040931300009106053,
+                                                                    "total": 0.00038448899977083784,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00040931300009106053
+                                                                    "self": 0.00038448899977083784
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.03680342899997413,
+                                                                    "total": 0.03221951200066542,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.03680342899997413
+                                                                    "self": 0.03221951200066542
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0018906959999185347,
+                                                                    "total": 0.0017899419999594102,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003501900000628666,
+                                                                    "self": 0.00035050699898420135,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001540505999855668,
+                                                                            "total": 0.0014394350009752088,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001540505999855668
+                                                                            "self": 0.0014394350009752088
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 21.440922833004606,
-                                                    "count": 1863,
+                                                    "total": 214.61526734999825,
+                                                    "count": 18191,
                                                     "is_parallel": true,
-                                                    "self": 1.0137311140074416,
+                                                    "self": 9.955182770026113,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 0.5540877439839278,
-                                                            "count": 1863,
+                                                            "total": 5.758412056036832,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 0.5540877439839278
+                                                            "self": 5.758412056036832
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 16.59735459800777,
-                                                            "count": 1863,
+                                                            "total": 165.37675128694082,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 16.59735459800777
+                                                            "self": 165.37675128694082
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 3.275749377005468,
-                                                            "count": 1863,
+                                                            "total": 33.52492123699449,
+                                                            "count": 18191,
                                                             "is_parallel": true,
-                                                            "self": 0.5869593910292679,
+                                                            "self": 6.077929993055477,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 2.6887899859762,
-                                                                    "count": 18630,
+                                                                    "total": 27.44699124393901,
+                                                                    "count": 181910,
                                                                     "is_parallel": true,
-                                                                    "self": 2.6887899859762
+                                                                    "self": 27.44699124393901
                                                                 }
                                                             }
                                                         }
@@ -307,31 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 13.35483704800572,
-                            "count": 1864,
-                            "self": 0.04525963401692934,
+                            "total": 137.62348767598178,
+                            "count": 18192,
+                            "self": 0.4672868959187326,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 3.373070740989988,
-                                    "count": 1864,
-                                    "self": 2.881808480990003,
+                                    "total": 37.05739246905887,
+                                    "count": 18192,
+                                    "self": 36.65069941405909,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.49126225999998496,
+                                            "total": 0.4066930549997778,
                                             "count": 4,
-                                            "self": 0.49126225999998496
+                                            "self": 0.4066930549997778
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 9.936506672998803,
-                                    "count": 9,
-                                    "self": 3.8466351470005975,
+                                    "total": 100.09880831100418,
+                                    "count": 90,
+                                    "self": 40.685734841027624,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 6.0898715259982055,
-                                            "count": 456,
-                                            "self": 6.0898715259982055
+                                            "total": 59.41307346997655,
+                                            "count": 4587,
+                                            "self": 59.41307346997655
                                         }
                                     }
                                 }
@@ -340,19 +340,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.1199999789823778e-06,
+                    "total": 9.760005923453718e-07,
                     "count": 1,
-                    "self": 1.1199999789823778e-06
+                    "self": 9.760005923453718e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.09037369899988335,
+                    "total": 0.09354297100071562,
                     "count": 1,
-                    "self": 0.0008995179996418301,
+                    "self": 0.0012433800002327189,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.08947418100024151,
+                            "total": 0.0922995910004829,
                             "count": 1,
-                            "self": 0.08947418100024151
+                            "self": 0.0922995910004829
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,58 +2,58 @@
     "SnowballTarget": {
         "checkpoints": [
             {
-                "steps": 4976,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-4976.onnx",
-                "reward": 3.090909090909091,
-                "creation_time": 1739012557.8850245,
+                "steps": 49968,
+                "file_path": "results/my_run_id/SnowballTarget/SnowballTarget-49968.onnx",
+                "reward": 14.636363636363637,
+                "creation_time": 1739015513.96152,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-4976.pt"
+                    "results/my_run_id/SnowballTarget/SnowballTarget-49968.pt"
                 ]
             },
             {
-                "steps": 9952,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-9952.onnx",
-                "reward": 4.909090909090909,
-                "creation_time": 1739012570.0554163,
+                "steps": 99992,
+                "file_path": "results/my_run_id/SnowballTarget/SnowballTarget-99992.onnx",
+                "reward": 20.818181818181817,
+                "creation_time": 1739015635.9993365,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-9952.pt"
+                    "results/my_run_id/SnowballTarget/SnowballTarget-99992.pt"
                 ]
             },
             {
-                "steps": 14992,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-14992.onnx",
-                "reward": 6.363636363636363,
-                "creation_time": 1739012581.0289712,
+                "steps": 149984,
+                "file_path": "results/my_run_id/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 25.545454545454547,
+                "creation_time": 1739015752.2613852,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-14992.pt"
+                    "results/my_run_id/SnowballTarget/SnowballTarget-149984.pt"
                 ]
             },
             {
-                "steps": 19992,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-19992.onnx",
-                "reward": 5.2727272727272725,
-                "creation_time": 1739012593.2567124,
+                "steps": 199984,
+                "file_path": "results/my_run_id/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 25.272727272727273,
+                "creation_time": 1739015864.0978277,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-19992.pt"
+                    "results/my_run_id/SnowballTarget/SnowballTarget-199984.pt"
                 ]
             },
             {
-                "steps": 20504,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-20504.onnx",
-                "reward": 5.2727272727272725,
-                "creation_time": 1739012593.3971872,
+                "steps": 200112,
+                "file_path": "results/my_run_id/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 25.272727272727273,
+                "creation_time": 1739015864.2073863,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-20504.pt"
+                    "results/my_run_id/SnowballTarget/SnowballTarget-200112.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 20504,
-            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 5.2727272727272725,
-            "creation_time": 1739012593.3971872,
+            "steps": 200112,
+            "file_path": "results/my_run_id/SnowballTarget.onnx",
+            "reward": 25.272727272727273,
+            "creation_time": 1739015864.2073863,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-20504.pt"
+                "results/my_run_id/SnowballTarget/SnowballTarget-200112.pt"
             ]
         }
     },