Updated model

.gitattributes

@@ -38,3 +38,9 @@ SnowballTarget/SnowballTarget-199984.onnx.data filter=lfs diff=lfs merge=lfs -te
 SnowballTarget/SnowballTarget-200240.onnx.data filter=lfs diff=lfs merge=lfs -text
 SnowballTarget/SnowballTarget-49936.onnx.data filter=lfs diff=lfs merge=lfs -text
 SnowballTarget/SnowballTarget-99936.onnx.data filter=lfs diff=lfs merge=lfs -text
+SnowballTarget/SnowballTarget-149984.onnx.data filter=lfs diff=lfs merge=lfs -text
+SnowballTarget/SnowballTarget-249944.onnx.data filter=lfs diff=lfs merge=lfs -text
+SnowballTarget/SnowballTarget-26400.onnx.data filter=lfs diff=lfs merge=lfs -text
+SnowballTarget/SnowballTarget-299968.onnx.data filter=lfs diff=lfs merge=lfs -text
+SnowballTarget/SnowballTarget-319192.onnx.data filter=lfs diff=lfs merge=lfs -text
+SnowballTarget/SnowballTarget-99960.onnx.data filter=lfs diff=lfs merge=lfs -text

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d4701d0ef34d1fc7767a17507b3807fade4be66ac12399835e87f76d87fcb0e
-size 62838
+oid sha256:4589ed51e34f079a3906f3250f747a0624b8421b89ffd54b7dc3495e700af4a8
+size 1815958

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61248c4a37f5ba55729692bfd20b7052b75628c4c88eac578927fcd5d46725f3
+size 1815958

SnowballTarget/SnowballTarget-149984.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f1f58a57041f581e0885fc989497e7b52f044f0d99a201de5e9c89f47282d7a
+size 1806336

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab4a02d0dfb39890c291cd11837064dab55bfff36867a1197156ccddfaffe824
+size 10820443

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb48a8c4bd479ec5ba5ac4c4a73d14a72d64adbfc38b74558cf9727e74003f39
-size 62838
+oid sha256:282fec681271870cdac8fcda4a10d50112284bccbda99999c8a799ed873fc88c
+size 1815958

SnowballTarget/SnowballTarget-199984.onnx.data

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2308d3c3424c7319b4160450785ac60f43f8f50a00753b5e3afefd6cdc31576c
-size 641024
+oid sha256:7e1fbcc58a9fd2671b1ba8a693d374318b00e83dda6849d0aad12939de3b79db
+size 1806336

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fbb0e36564ff3cf5085f6bbcef1cefd8012f0eea2b72581a18d90759184f2f6
-size 3850564
+oid sha256:9494cb348101165f11224a6d212ee1944542fddfeb0304c8e92608341d38127a
+size 10820443

SnowballTarget/SnowballTarget-249944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:770e752ca6fa4a542064d82db732601b3d5b3e3b7bf93a8c75a637308a7ba89d
+size 1815958

SnowballTarget/SnowballTarget-249944.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23a75160d7d88e5400b2326ea55287b1046cdb215f24a7923b8e23a846e15bfb
+size 1806336

SnowballTarget/SnowballTarget-249944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99184268379dd1ee0ca500027d144e351d2eba2a5e0d8d64b9df26bff0b9a578
+size 10820443

SnowballTarget/SnowballTarget-26400.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65fee282d447c7cc4ef5e285e799b45cc8594295ef9267ad214bb688caabbba2
+size 62831

SnowballTarget/SnowballTarget-26400.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59511bd2ce34e2becd9fdf8606f27114c3a3719aa961d7384067a6b0f5a314b7
+size 641024

SnowballTarget/SnowballTarget-26400.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bea03e38a347e1775953e556c129ac6e605bf49ed73468926a99e7a5737816b9
+size 3850487

SnowballTarget/SnowballTarget-299968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d925d859fd3f96e44bd3b77be4f99e3183dfc6f42627ef77c87229e36764091
+size 1815958

SnowballTarget/SnowballTarget-299968.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c73be9c6ac05feecfa5c2b4602afe746f3ae364c386f123bf9f4a8eda86ad4d7
+size 1806336

SnowballTarget/SnowballTarget-299968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6ebbc0244210bbf28258b3fd77de7180e451e2f8e078dd2cfb8516f09f42747
+size 10820443

SnowballTarget/SnowballTarget-319192.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9941ad257489f80a635efd535f6291ec7d25cb440a398327ff349e8ffb4dc4c
+size 62840

SnowballTarget/SnowballTarget-319192.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c73be9c6ac05feecfa5c2b4602afe746f3ae364c386f123bf9f4a8eda86ad4d7
+size 1806336

SnowballTarget/SnowballTarget-319192.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f043b902ee5efb4e2cd5378c9ea19cc6ab6464c9f1bb11129c331407dadde18
+size 10820932

SnowballTarget/SnowballTarget-349992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f771f58ae4d97774a39f5fd06394ee6893866c404ebe3f86f971928ae72e9b4a
+size 1815958

SnowballTarget/SnowballTarget-349992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3cf857587e3f68310126bc51c1a66a56b394bb57c5381ed3cc873cece97cf84
+size 10820443

SnowballTarget/SnowballTarget-399992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5fc58b11adcede2d1901c05598a412232e4e256a612cb11973ea76a5bc6e7d7
+size 1815958

SnowballTarget/SnowballTarget-399992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4b027b06539d83d6f9fef385d6e030a7d0fa43b53815c6c3a7399aba40b28ee
+size 10820443

SnowballTarget/SnowballTarget-449952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cb650b9862918261a3f89214ee9412e8a81fe83ec05838ce2b8d67c3685e3aa
+size 1815958

SnowballTarget/SnowballTarget-449952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1ed0befb6667374c6461fa84fa1bc0c0788de23945e3265beaf4e560876f0bc
+size 10820443

SnowballTarget/SnowballTarget-49936.onnx.data

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12b522799ac33a2fd4cdee9ab17bfd816e955390099cffb9d2c9f461b18219e9
-size 641024
+oid sha256:43b258a09cf3a6d4ea79a6f25be2cb9d633e3a3b0bc6cbc6a0fbc83554cc095a
+size 1806336

SnowballTarget/SnowballTarget-499976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4589ed51e34f079a3906f3250f747a0624b8421b89ffd54b7dc3495e700af4a8
+size 1815958

SnowballTarget/SnowballTarget-499976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec9f4fda5a0f2d3c6f54bd7ee64b7c0e0b4797fdc982935b8322fa954951af03
+size 10820443

SnowballTarget/SnowballTarget-500104.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4589ed51e34f079a3906f3250f747a0624b8421b89ffd54b7dc3495e700af4a8
+size 1815958

SnowballTarget/SnowballTarget-500104.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d9eecd3f09126843e7b0e79945f8c584d8d5b46d535ef3b4f66ce9871d080e2
+size 10820443

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d44097963c8568eddc7035817102564e028051b4e69d3f8eced5e24ddd8ec4a2
+size 1815958

SnowballTarget/SnowballTarget-99960.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f268044b2441f0b88dcd338bcd1f15ef40ba71a51a6f47540d66b71794e7020
+size 1806336

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94120a8366dcb8563432d9f183f145480dc6978220142f6b9c8fc988a9e88a46
+size 10820368

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9143fc7ce327a04893636630412a2fdb6d033fcdd224455ad6d9d9385c51b934
-size 3849717
+oid sha256:ff7676ef75c6780c845f1ecfc01942ee35225b343ae1ba1f74b70ed86f5b1cdc
+size 10819618

SnowballTarget/events.out.tfevents.1760689715.auriga.367238.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41a3c62052f013ecb3bfb26b142bad92929b952b49f1008ee0b9256a35b5cbea
+size 81505

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": 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": 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": 512, "buffer_size": 32768, "learning_rate": 0.0001, "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": 512, "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": 500000, "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": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -3,9 +3,9 @@ behaviors:
   SnowballTarget:
     trainer_type: ppo
     hyperparameters:
-      batch_size: 128
-      buffer_size: 2048
-      learning_rate: 0.0003
+      batch_size: 512
+      buffer_size: 32768
+      learning_rate: 0.0001
       beta: 0.005
       epsilon: 0.2
       lambd: 0.95
@@ -17,7 +17,7 @@ behaviors:
     checkpoint_interval: 50000
     network_settings:
       normalize: false
-      hidden_units: 256
+      hidden_units: 512
       num_layers: 2
       vis_encode_type: simple
       memory: null
@@ -38,7 +38,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 10
     even_checkpoints: false
-    max_steps: 200000
+    max_steps: 500000
     time_horizon: 64
     summary_freq: 10000
     threaded: false
@@ -69,8 +69,8 @@ checkpoint_settings:
   run_id: SnowballTarget1
   initialize_from: null
   load_model: false
-  resume: true
-  force: false
+  resume: false
+  force: true
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -11,7 +11,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.093 seconds
+- Completed reload, in  0.099 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)
@@ -22,7 +22,7 @@ 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: 1.104540 ms
+UnloadTime: 1.286488 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 24 worker threads for Enlighten.
@@ -30,16 +30,11 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 4031 frames, [16.0 KB-32.0 KB]: 68 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 13412 frames, [16.0 KB-32.0 KB]: 227 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
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 19]
-      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 18]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
@@ -55,6 +50,11 @@ Memory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 3.6 KB
       Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 282 B
+      Overflow Count 0
     [ALLOC_TEMP_Job.Worker 44]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
@@ -220,12 +220,12 @@ Memory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 3.6 KB
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 21]
+    [ALLOC_TEMP_Job.Worker 26]
       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 26]
+    [ALLOC_TEMP_Job.Worker 21]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 3.6 KB
@@ -235,7 +235,7 @@ Memory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 3.6 KB
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 14]
+    [ALLOC_TEMP_Background Job.Worker 9]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -250,11 +250,6 @@ Memory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 3.6 KB
       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 34]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
@@ -265,6 +260,11 @@ Memory Statistics:
       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
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
     [ALLOC_TEMP_Job.Worker 29]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
@@ -350,12 +350,17 @@ Memory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 3.6 KB
       Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 24]
+      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 15]
       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 24]
+    [ALLOC_TEMP_Job.Worker 19]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 3.6 KB
@@ -370,28 +375,23 @@ Memory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 3.6 KB
       Overflow Count 0
-    [ALLOC_TEMP_Loading.AsyncRead]
-      Initial Block Size 64.0 KB
-      Current Block Size 64.0 KB
-      Peak Allocated Bytes 282 B
-      Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 36
+  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]: 4100 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 9983 frames, [8.0 MB-16.0 MB]: 3657 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 6.6 MB
+      Peak Allocated memory 9.9 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 4100 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 13640 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.5 MB
+      Peak Allocated memory 17.4 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -420,13 +420,13 @@ 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]: 3482 frames, [64.0 KB-128.0 KB]: 618 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 10849 frames, [64.0 KB-128.0 KB]: 2791 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 67.3 KB
+      Peak Allocated memory 67.2 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 4100 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 13640 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -438,13 +438,13 @@ 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]: 4100 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 13640 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]: 4099 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 13639 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
@@ -456,13 +456,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 4100 frames
+      Peak usage frame count: [0-1.0 KB]: 13640 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]: 4100 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 13640 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": 0.9344794154167175,
-            "min": 0.9344794154167175,
-            "max": 2.153480291366577,
-            "count": 16
+            "value": 1.8568122386932373,
+            "min": 1.8568122386932373,
+            "max": 2.8903470039367676,
+            "count": 50
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 8963.5263671875,
-            "min": 1516.0501708984375,
-            "max": 19536.798828125,
-            "count": 16
+            "value": 17810.54296875,
+            "min": 17775.48046875,
+            "max": 29759.01171875,
+            "count": 50
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 499976.0,
+            "min": 9952.0,
+            "max": 499976.0,
+            "count": 50
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 499976.0,
+            "min": 9952.0,
+            "max": 499976.0,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 6.018762111663818,
+            "min": -0.017574388533830643,
+            "max": 6.018762111663818,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 1233.84619140625,
+            "min": -3.602749824523926,
+            "max": 1233.84619140625,
+            "count": 50
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 50
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 10945.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 50
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 17.672727272727272,
+            "min": 2.727272727272727,
+            "max": 18.181818181818183,
+            "count": 50
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 972.0,
+            "min": 120.0,
+            "max": 972.0,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 17.672727272727272,
+            "min": 2.727272727272727,
+            "max": 18.181818181818183,
+            "count": 50
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 972.0,
+            "min": 120.0,
+            "max": 972.0,
+            "count": 50
         },
         "SnowballTarget.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 16
+            "count": 50
         },
         "SnowballTarget.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 16
-        },
-        "SnowballTarget.Step.mean": {
-            "value": 199984.0,
-            "min": 59952.0,
-            "max": 199984.0,
-            "count": 15
-        },
-        "SnowballTarget.Step.sum": {
-            "value": 199984.0,
-            "min": 59952.0,
-            "max": 199984.0,
-            "count": 15
-        },
-        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 12.326292037963867,
-            "min": 5.530655384063721,
-            "max": 12.326292037963867,
-            "count": 15
-        },
-        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2526.889892578125,
-            "min": 1078.477783203125,
-            "max": 2526.889892578125,
-            "count": 15
+            "count": 50
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.07485539761837573,
-            "min": 0.0676656143312036,
-            "max": 0.07485539761837573,
+            "value": 0.035475623733418615,
+            "min": 0.03180414954922147,
+            "max": 0.03817954923768715,
             "count": 15
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.37427698809187865,
-            "min": 0.2706624573248144,
-            "max": 0.37427698809187865,
+            "value": 0.035475623733418615,
+            "min": 0.03180414954922147,
+            "max": 0.03817954923768715,
             "count": 15
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.176937632058181,
-            "min": 0.176937632058181,
-            "max": 0.2733584906969804,
+            "value": 0.3183900256020327,
+            "min": 0.08703206747304648,
+            "max": 0.3183900256020327,
             "count": 15
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.884688160290905,
-            "min": 0.7650682372497578,
-            "max": 1.3637838930475945,
+            "value": 0.3183900256020327,
+            "min": 0.08703206747304648,
+            "max": 0.3183900256020327,
             "count": 15
         },
         "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 7.428097524e-06,
-            "min": 7.428097524e-06,
-            "max": 0.000216978027674,
+            "value": 1.0176989823999964e-06,
+            "min": 1.0176989823999964e-06,
+            "max": 9.341760658240001e-05,
             "count": 15
         },
         "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 3.714048762e-05,
-            "min": 3.714048762e-05,
-            "max": 0.00101064016312,
+            "value": 1.0176989823999964e-06,
+            "min": 1.0176989823999964e-06,
+            "max": 9.341760658240001e-05,
             "count": 15
         },
         "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10247600000000001,
-            "min": 0.10247600000000001,
-            "max": 0.172326,
+            "value": 0.10101760000000003,
+            "min": 0.10101760000000003,
+            "max": 0.19341760000000005,
             "count": 15
         },
         "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.5123800000000001,
-            "min": 0.429704,
-            "max": 0.8368800000000001,
+            "value": 0.10101760000000003,
+            "min": 0.10101760000000003,
+            "max": 0.19341760000000005,
             "count": 15
         },
         "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.00013355240000000005,
-            "min": 0.00013355240000000005,
-            "max": 0.0036190674000000003,
+            "value": 6.077823999999984e-05,
+            "min": 6.077823999999984e-05,
+            "max": 0.004671538240000001,
             "count": 15
         },
         "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.0006677620000000002,
-            "min": 0.0006677620000000002,
-            "max": 0.016860312000000002,
-            "count": 15
-        },
-        "SnowballTarget.Environment.EpisodeLength.mean": {
-            "value": 199.0,
-            "min": 199.0,
-            "max": 199.0,
-            "count": 15
-        },
-        "SnowballTarget.Environment.EpisodeLength.sum": {
-            "value": 10945.0,
-            "min": 8756.0,
-            "max": 10945.0,
-            "count": 15
-        },
-        "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 24.30909090909091,
-            "min": 14.772727272727273,
-            "max": 24.30909090909091,
-            "count": 15
-        },
-        "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1337.0,
-            "min": 650.0,
-            "max": 1337.0,
-            "count": 15
-        },
-        "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 24.30909090909091,
-            "min": 14.772727272727273,
-            "max": 24.30909090909091,
-            "count": 15
-        },
-        "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1337.0,
-            "min": 650.0,
-            "max": 1337.0,
+            "value": 6.077823999999984e-05,
+            "min": 6.077823999999984e-05,
+            "max": 0.004671538240000001,
             "count": 15
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1760687063",
+        "start_time_seconds": "1760689714",
         "python_version": "3.10.12 (main, Aug 15 2025, 14:32:43) [GCC 11.4.0]",
-        "command_line_arguments": "/local_scratch/ahmohame/MyRLProj/.venv/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
+        "command_line_arguments": "/local_scratch/ahmohame/MyRLProj/.venv/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
-        "pytorch_version": "2.9.0+cu128",
+        "pytorch_version": "2.3.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1760687495"
+        "end_time_seconds": "1760690960"
     },
-    "total": 432.1884180130437,
+    "total": 1246.1255109719932,
     "count": 1,
-    "self": 0.37457607907708734,
+    "self": 0.374010790954344,
     "children": {
         "run_training.setup": {
-            "total": 0.026659096009097993,
+            "total": 0.02128842705860734,
             "count": 1,
-            "self": 0.026659096009097993
+            "self": 0.02128842705860734
         },
         "TrainerController.start_learning": {
-            "total": 431.7871828379575,
+            "total": 1245.7302117539803,
             "count": 1,
-            "self": 0.19716291455551982,
+            "self": 0.6739412506576627,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.315003640949726,
+                    "total": 2.9158263229765,
                     "count": 1,
-                    "self": 2.315003640949726
+                    "self": 2.9158263229765
                 },
                 "TrainerController.advance": {
-                    "total": 427.82484198745806,
-                    "count": 13664,
-                    "self": 0.20069539861287922,
+                    "total": 1242.0460719174007,
+                    "count": 45464,
+                    "self": 0.6814981006318703,
                     "children": {
                         "env_step": {
-                            "total": 310.37624442589004,
-                            "count": 13664,
-                            "self": 271.7278343383223,
+                            "total": 1054.3282872018171,
+                            "count": 45464,
+                            "self": 919.0131197725423,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 38.51920480164699,
-                                    "count": 13664,
-                                    "self": 0.6734598745824769,
+                                    "total": 134.8636818312807,
+                                    "count": 45464,
+                                    "self": 2.2304799418197945,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 37.845744927064516,
-                                            "count": 13664,
-                                            "self": 37.845744927064516
+                                            "total": 132.6332018894609,
+                                            "count": 45464,
+                                            "self": 132.6332018894609
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.12920528592076153,
-                                    "count": 13664,
+                                    "total": 0.45148559799417853,
+                                    "count": 45464,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 428.1941619500285,
-                                            "count": 13664,
+                                            "total": 1243.1112274315674,
+                                            "count": 45464,
                                             "is_parallel": true,
-                                            "self": 178.94030459946953,
+                                            "self": 398.501711131772,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.004295137012377381,
+                                                            "total": 0.00440782296936959,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0011666940990835428,
+                                                            "self": 0.0011371220462024212,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0031284429132938385,
+                                                                    "total": 0.003270700923167169,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0031284429132938385
+                                                                    "self": 0.003270700923167169
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04597055108752102,
+                                                            "total": 0.04261121794115752,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0008726851083338261,
+                                                            "self": 0.0009077248396351933,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0006993829738348722,
+                                                                    "total": 0.0006594400620087981,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0006993829738348722
+                                                                    "self": 0.0006594400620087981
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04149426205549389,
+                                                                    "total": 0.03817833599168807,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04149426205549389
+                                                                    "self": 0.03817833599168807
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.002904220949858427,
+                                                                    "total": 0.0028657170478254557,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005674530984833837,
+                                                                    "self": 0.0005921600386500359,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0023367678513750434,
+                                                                            "total": 0.00227355700917542,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0023367678513750434
+                                                                            "self": 0.00227355700917542
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 249.25385735055897,
-                                                    "count": 13663,
+                                                    "total": 844.6095162997954,
+                                                    "count": 45463,
                                                     "is_parallel": true,
-                                                    "self": 9.961991776013747,
+                                                    "self": 35.7958256395068,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 6.230835664086044,
-                                                            "count": 13663,
+                                                            "total": 21.017438556067646,
+                                                            "count": 45463,
                                                             "is_parallel": true,
-                                                            "self": 6.230835664086044
+                                                            "self": 21.017438556067646
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 201.06483742501587,
-                                                            "count": 13663,
+                                                            "total": 676.2517781199422,
+                                                            "count": 45463,
                                                             "is_parallel": true,
-                                                            "self": 201.06483742501587
+                                                            "self": 676.2517781199422
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 31.996192485443316,
-                                                            "count": 13663,
+                                                            "total": 111.54447398427874,
+                                                            "count": 45463,
                                                             "is_parallel": true,
-                                                            "self": 6.077628318686038,
+                                                            "self": 21.141052892548032,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 25.918564166757278,
-                                                                    "count": 136630,
+                                                                    "total": 90.4034210917307,
+                                                                    "count": 454630,
                                                                     "is_parallel": true,
-                                                                    "self": 25.918564166757278
+                                                                    "self": 90.4034210917307
                                                                 }
                                                             }
                                                         }
@@ -307,31 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 117.24790216295514,
-                            "count": 13664,
-                            "self": 0.27291102579329163,
+                            "total": 187.03628661495168,
+                            "count": 45464,
+                            "self": 0.7960933083668351,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 23.37360843643546,
-                                    "count": 13664,
-                                    "self": 15.879194783512503,
+                                    "total": 50.32543419068679,
+                                    "count": 45464,
+                                    "self": 49.403155541745946,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 7.494413652922958,
-                                            "count": 4,
-                                            "self": 7.494413652922958
+                                            "total": 0.9222786489408463,
+                                            "count": 10,
+                                            "self": 0.9222786489408463
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 93.60138270072639,
-                                    "count": 68,
-                                    "self": 23.973814754164778,
+                                    "total": 135.91475911589805,
+                                    "count": 15,
+                                    "self": 79.53988587856293,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 69.62756794656161,
-                                            "count": 3465,
-                                            "self": 69.62756794656161
+                                            "total": 56.37487323733512,
+                                            "count": 2880,
+                                            "self": 56.37487323733512
                                         }
                                     }
                                 }
@@ -340,19 +340,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.710201993584633e-07,
+                    "total": 8.719507604837418e-07,
                     "count": 1,
-                    "self": 9.710201993584633e-07
+                    "self": 8.719507604837418e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 1.4501733239740133,
+                    "total": 0.0943713909946382,
                     "count": 1,
-                    "self": 0.0005577360279858112,
+                    "self": 0.0012160909827798605,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 1.4496155879460275,
+                            "total": 0.09315530001185834,
                             "count": 1,
-                            "self": 1.4496155879460275
+                            "self": 0.09315530001185834
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,65 +1,110 @@
 {
-    "metadata": {
-        "stats_format_version": "0.3.0",
-        "mlagents_version": "1.2.0.dev0",
-        "torch_version": "2.9.0+cu128"
-    },
     "SnowballTarget": {
         "checkpoints": [
             {
-                "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": null,
-                "creation_time": 1760687071.1677175,
+                "steps": 99960,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 4.2727272727272725,
+                "creation_time": 1760689965.875995,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
                 ]
             },
             {
-                "steps": 99936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99936.onnx",
-                "reward": 19.90909090909091,
-                "creation_time": 1760687214.6778388,
+                "steps": 149984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 8.373737373737374,
+                "creation_time": 1760690084.296909,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99936.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
                 ]
             },
             {
-                "steps": 149960,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149960.onnx",
-                "reward": 23.727272727272727,
-                "creation_time": 1760687348.7690995,
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 10.363636363636363,
+                "creation_time": 1760690215.7909374,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149960.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
                 ]
             },
             {
-                "steps": 199984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 25.181818181818183,
-                "creation_time": 1760687494.144507,
+                "steps": 249944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.onnx",
+                "reward": 12.494949494949495,
+                "creation_time": 1760690337.2152503,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-249944.pt"
+                ]
+            },
+            {
+                "steps": 299968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.onnx",
+                "reward": 13.272727272727273,
+                "creation_time": 1760690461.3641863,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-299968.pt"
+                ]
+            },
+            {
+                "steps": 349992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.onnx",
+                "reward": 14.745454545454546,
+                "creation_time": 1760690583.665323,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-349992.pt"
+                ]
+            },
+            {
+                "steps": 399992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.onnx",
+                "reward": 16.727272727272727,
+                "creation_time": 1760690704.0682063,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-399992.pt"
+                ]
+            },
+            {
+                "steps": 449952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.onnx",
+                "reward": 17.263636363636362,
+                "creation_time": 1760690823.7661152,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-449952.pt"
                 ]
             },
             {
-                "steps": 200240,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200240.onnx",
-                "reward": 25.181818181818183,
-                "creation_time": 1760687495.6147425,
+                "steps": 499976,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.onnx",
+                "reward": 18.272727272727273,
+                "creation_time": 1760690960.1838775,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200240.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-499976.pt"
+                ]
+            },
+            {
+                "steps": 500104,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.onnx",
+                "reward": 18.272727272727273,
+                "creation_time": 1760690960.2877028,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 200240,
+            "steps": 500104,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 25.181818181818183,
-            "creation_time": 1760687495.6147425,
+            "reward": 18.272727272727273,
+            "creation_time": 1760690960.2877028,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200240.pt"
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-500104.pt"
             ]
         }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.3.1+cu121"
     }
 }