run5

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e038a9e36e91b807a82bf3158a92856090d77a335b33b945ffec9cc8f64b9ef0
+oid sha256:acabf98140a6dc8ab34f9f2c68cdb740bedc5635763d13106971e2699b5c6f21
 size 645119

SnowballTarget/{SnowballTarget-149984.onnx → SnowballTarget-1599976.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02abbe8672d5f82480297b463fee125f687959d5843fe12520614b2a309f6d13
+oid sha256:7933853f98178301d95060023013db82b527b77fa06f17738fe2943855c490c1
 size 645119

SnowballTarget/{SnowballTarget-200112.pt → SnowballTarget-1599976.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fbea28e9a3c8b6adef2503f2f41fa7453d1f83c0a61c87f36dd907a7ab20e2d
+oid sha256:10c86fe78bc1226ed4779d8d08689f768ab09d883c46085972e0619e1d0a243a
 size 3844788

SnowballTarget/{SnowballTarget-200112.onnx → SnowballTarget-1649992.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e038a9e36e91b807a82bf3158a92856090d77a335b33b945ffec9cc8f64b9ef0
+oid sha256:3ab4c6b348a63561d55a1695bb8c1be8c990005436e6af9b125d8a8c74151d5f
 size 645119

SnowballTarget/{SnowballTarget-149984.pt → SnowballTarget-1649992.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daf4da98e80f7ad24eb82cdd048f4696dd42023105ec24d5db5ad52cd1baf244
+oid sha256:08829efcb81b159036fd83ea2035db6738f9fef870f0dc7fd7c3259cab8e241e
 size 3844788

SnowballTarget/{SnowballTarget-199984.onnx → SnowballTarget-1699936.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e038a9e36e91b807a82bf3158a92856090d77a335b33b945ffec9cc8f64b9ef0
+oid sha256:3721232ff4cad21c66d35474dcac52002cef30b7a78bf7038b6459d14eedfca7
 size 645119

SnowballTarget/{SnowballTarget-49936.pt → SnowballTarget-1699936.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fca67d8cc7fc3d6db4e876ea8dcef5a9300b88e5720d04b8acc2ff0ee9cbf90b
+oid sha256:76d6660f41179480ea3da7519f9c44b388054b7f359c178e6cfb1b54489e7cc7
 size 3844788

SnowballTarget/{SnowballTarget-49936.onnx → SnowballTarget-1749960.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18e1e682f9a68e172a4cf85140596baad59dc6963864de325620a0d199a42100
+oid sha256:45f87a792b86aa7fc5625320232453d0d71459353fde8fc47e6d3cc3adbee6b8
 size 645119

SnowballTarget/{SnowballTarget-199984.pt → SnowballTarget-1749960.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd9b10096e9c99f6c05d8527f28f128ba45687a13b92e24117c9e48ac3450f6f
+oid sha256:d6d3577c9354eedb5be3da4f4770a961432492bd6f51693aa950b9f7b86d8fd4
 size 3844788

SnowballTarget/SnowballTarget-1799984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7580bb27200b65ae3a8c26bab14ed7023d66a6a9a54d39dd837592a6f1fe3ec3
+size 645119

SnowballTarget/SnowballTarget-1799984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0455f06960f461a7a0de8f59bbf9d7aa8cdbec03f1ec9f5034521cc5eed6183
+size 3844788

SnowballTarget/SnowballTarget-1849984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1adda266c50c8490c4da7c4489f4cc2097318addbd67cc79f038e56e293b4cb9
+size 645119

SnowballTarget/SnowballTarget-1849984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3cca88014eaac491218345ba618b91efd116982db883512a435c1b8f2bdcfb8
+size 3844788

SnowballTarget/SnowballTarget-1899944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34b724efc9c127cf9ad586af51783d46f1535e8f9623a933b621aef8d6094136
+size 645119

SnowballTarget/SnowballTarget-1899944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4927af5f83c62881111b940b56fe7e94c7db70802cd1416dc1764e0b7f935043
+size 3844788

SnowballTarget/SnowballTarget-1949968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e716baaef7e7b98c4ed8b0f303a1bdff26fb071a720f1a999f818503272a2e26
+size 645119

SnowballTarget/SnowballTarget-1949968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ea4e3dab9ced3cce4002f2433e8660ff1158776cf9b3d2ed0de58c37fda5c22
+size 3844788

SnowballTarget/SnowballTarget-1999992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acabf98140a6dc8ab34f9f2c68cdb740bedc5635763d13106971e2699b5c6f21
+size 645119

SnowballTarget/SnowballTarget-1999992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:379665e081fde322f42d5c7c5d8fc3d5660500fbb2a7aa213eb917e92772cf43
+size 3844788

SnowballTarget/SnowballTarget-2000376.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acabf98140a6dc8ab34f9f2c68cdb740bedc5635763d13106971e2699b5c6f21
+size 645119

SnowballTarget/SnowballTarget-2000376.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f042d4d81496589845355f39b74993dc72222d318356823bda4427ae06cd6416
+size 3844788

SnowballTarget/SnowballTarget-99960.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:32b8e7940773ef088459ab5cfa04ed4f71bce716b79437d271cd517b982c4584
-size 645119

SnowballTarget/SnowballTarget-99960.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:af456fc03156ba029aa9ea30a62d2b3640e36797de4760f2078db0bf8264ddf4
-size 3844788

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fbea28e9a3c8b6adef2503f2f41fa7453d1f83c0a61c87f36dd907a7ab20e2d
+oid sha256:f042d4d81496589845355f39b74993dc72222d318356823bda4427ae06cd6416
 size 3844788

SnowballTarget/events.out.tfevents.1673800027.lamarmite.457457.0

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b7c18cfd2d136275800949cc0d0b7a6c0bf3aeacd483e403701f1741a3739e9c
-size 23957

SnowballTarget/events.out.tfevents.1673823722.lamarmite.489332.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b846d79ba1385ed590cd2eddd2fa66e17fe3aa100a4ba4ca33632a59370a843
+size 170111

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, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 50000, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0002, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 50000, "max_steps": 2000000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget5", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -5,7 +5,7 @@ behaviors:
     hyperparameters:
       batch_size: 128
       buffer_size: 2048
-      learning_rate: 0.0003
+      learning_rate: 0.0002
       beta: 0.005
       epsilon: 0.2
       lambd: 0.95
@@ -36,7 +36,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 10
     checkpoint_interval: 50000
-    max_steps: 200000
+    max_steps: 2000000
     time_horizon: 64
     summary_freq: 10000
     threaded: true
@@ -62,7 +62,7 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: SnowballTarget1
+  run_id: SnowballTarget5
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -2,9 +2,6 @@ Mono path[0] = '/home/emmanuel/Documents/code/rl/ml-agents/training-envs-executa
 Mono config path = '/home/emmanuel/Documents/code/rl/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: /home/emmanuel/.config/unity3d/Hugging Face
-PlayerPrefs - Creating folder: /home/emmanuel/.config/unity3d/Hugging Face/SnowballTarget
-Unable to load player prefs
 Initialize engine version: 2021.3.14f1 (eee1884e7226)
 [Subsystems] Discovering subsystems at path /home/emmanuel/Documents/code/rl/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -14,7 +11,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  1.742 seconds
+- Completed reload, in  0.870 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)
@@ -25,7 +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: 2.055541 ms
+UnloadTime: 0.896450 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 2 worker threads for Enlighten.
@@ -33,7 +30,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 5370 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 53653 frames, [16.0 KB-32.0 KB]: 909 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
@@ -159,22 +156,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 45
+  Peak main deferred allocation count 41
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 5462 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 11046 frames, [8.0 MB-16.0 MB]: 27196 frames, [16.0 MB-32.0 MB]: 16321 frames
       Requested Block Size 16.0 MB
-      Peak Block count 1
-      Peak Allocated memory 7.0 MB
+      Peak Block count 2
+      Peak Allocated memory 24.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 5462 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 54563 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.4 MB
+      Peak Allocated memory 17.6 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -203,13 +200,13 @@ 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]: 4387 frames, [64.0 KB-128.0 KB]: 1075 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 52645 frames, [64.0 KB-128.0 KB]: 1918 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 66.8 KB
+      Peak Allocated memory 67.7 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 5462 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 54563 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -221,13 +218,13 @@ 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]: 5462 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 54563 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]: 5461 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 54562 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
@@ -239,13 +236,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 5462 frames
+      Peak usage frame count: [0-1.0 KB]: 54563 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]: 5462 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 54563 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -2,220 +2,220 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 1.0211290121078491,
-            "min": 1.0211290121078491,
-            "max": 2.854013204574585,
-            "count": 20
+            "value": 0.5959854125976562,
+            "min": 0.5709379315376282,
+            "max": 2.8557894229888916,
+            "count": 200
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 9783.4375,
-            "min": 9783.4375,
-            "max": 29227.94921875,
-            "count": 20
+            "value": 6129.7099609375,
+            "min": 5529.92138671875,
+            "max": 29246.140625,
+            "count": 200
         },
         "SnowballTarget.Step.mean": {
-            "value": 199984.0,
+            "value": 1999992.0,
             "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+            "max": 1999992.0,
+            "count": 200
         },
         "SnowballTarget.Step.sum": {
-            "value": 199984.0,
+            "value": 1999992.0,
             "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+            "max": 1999992.0,
+            "count": 200
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 12.06716251373291,
-            "min": 0.5820059776306152,
-            "max": 12.06716251373291,
-            "count": 20
+            "value": 14.251872062683105,
+            "min": 0.47750917077064514,
+            "max": 14.377264022827148,
+            "count": 200
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2353.0966796875,
-            "min": 112.9091567993164,
-            "max": 2436.14111328125,
-            "count": 20
+            "value": 2921.6337890625,
+            "min": 92.63677978515625,
+            "max": 2939.79443359375,
+            "count": 200
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
             "value": 199.0,
             "min": 199.0,
             "max": 199.0,
-            "count": 20
+            "count": 200
         },
         "SnowballTarget.Environment.EpisodeLength.sum": {
             "value": 10945.0,
             "min": 8756.0,
             "max": 10945.0,
-            "count": 20
+            "count": 200
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.06793563267887757,
-            "min": 0.06066728261865529,
-            "max": 0.07288110168227314,
-            "count": 20
+            "value": 0.07214724341619706,
+            "min": 0.06031834367476062,
+            "max": 0.07803036969657043,
+            "count": 200
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.2717425307155103,
-            "min": 0.24266913047462116,
-            "max": 0.35947661169955286,
-            "count": 20
+            "value": 0.3607362170809853,
+            "min": 0.24127337469904248,
+            "max": 0.37994980020623326,
+            "count": 200
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.2192965249950979,
-            "min": 0.12452422489649526,
-            "max": 0.3020132852389532,
-            "count": 20
+            "value": 0.14957752292062723,
+            "min": 0.11958930644608451,
+            "max": 0.272374791023778,
+            "count": 200
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.8771860999803917,
-            "min": 0.498096899585981,
-            "max": 1.3851492670455983,
-            "count": 20
+            "value": 0.7478876146031361,
+            "min": 0.47835722578433804,
+            "max": 1.3618739551188899,
+            "count": 200
         },
         "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 8.082097306000005e-06,
-            "min": 8.082097306000005e-06,
-            "max": 0.000291882002706,
-            "count": 20
+            "value": 4.688997656000026e-07,
+            "min": 4.688997656000026e-07,
+            "max": 0.0001994588002706,
+            "count": 200
         },
         "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 3.232838922400002e-05,
-            "min": 3.232838922400002e-05,
-            "max": 0.001385028038324,
-            "count": 20
+            "value": 2.344498828000013e-06,
+            "min": 2.344498828000013e-06,
+            "max": 0.000992344003828,
+            "count": 200
         },
         "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10269400000000001,
-            "min": 0.10269400000000001,
-            "max": 0.19729400000000002,
-            "count": 20
+            "value": 0.10023440000000002,
+            "min": 0.10023440000000002,
+            "max": 0.1997294,
+            "count": 200
         },
         "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.41077600000000003,
-            "min": 0.41077600000000003,
-            "max": 0.9616760000000001,
-            "count": 20
+            "value": 0.5011720000000001,
+            "min": 0.4029176,
+            "max": 0.996172,
+            "count": 200
         },
         "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.0001444306000000001,
-            "min": 0.0001444306000000001,
-            "max": 0.0048649706,
-            "count": 20
+            "value": 2.1696560000000067e-05,
+            "min": 2.1696560000000067e-05,
+            "max": 0.004986497059999999,
+            "count": 200
         },
         "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.0005777224000000004,
-            "min": 0.0005777224000000004,
-            "max": 0.0230876324,
-            "count": 20
+            "value": 0.00010848280000000034,
+            "min": 0.00010848280000000034,
+            "max": 0.024808982800000004,
+            "count": 200
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 24.068181818181817,
+            "value": 27.98181818181818,
             "min": 3.4318181818181817,
-            "max": 24.068181818181817,
-            "count": 20
+            "max": 28.509090909090908,
+            "count": 200
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1059.0,
+            "value": 1539.0,
             "min": 151.0,
-            "max": 1317.0,
-            "count": 20
+            "max": 1568.0,
+            "count": 200
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 24.068181818181817,
+            "value": 27.98181818181818,
             "min": 3.4318181818181817,
-            "max": 24.068181818181817,
-            "count": 20
+            "max": 28.509090909090908,
+            "count": 200
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1059.0,
+            "value": 1539.0,
             "min": 151.0,
-            "max": 1317.0,
-            "count": 20
+            "max": 1568.0,
+            "count": 200
         },
         "SnowballTarget.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 200
         },
         "SnowballTarget.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 200
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1673800023",
+        "start_time_seconds": "1673823719",
         "python_version": "3.8.16 (default, Dec  7 2022, 01:12:06) \n[GCC 11.3.0]",
-        "command_line_arguments": "/home/emmanuel/Documents/code/rl/ml-agents/venv/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "command_line_arguments": "/home/emmanuel/Documents/code/rl/ml-agents/venv/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget5 --no-graphics",
         "mlagents_version": "0.29.0.dev0",
         "mlagents_envs_version": "0.29.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.8.1+cu102",
         "numpy_version": "1.20.0",
-        "end_time_seconds": "1673800417"
+        "end_time_seconds": "1673827248"
     },
-    "total": 394.48205814900575,
+    "total": 3528.254173344001,
     "count": 1,
-    "self": 0.3803504949901253,
+    "self": 0.32245695596793666,
     "children": {
         "run_training.setup": {
-            "total": 0.01371243700850755,
+            "total": 0.12691729102516547,
             "count": 1,
-            "self": 0.01371243700850755
+            "self": 0.12691729102516547
         },
         "TrainerController.start_learning": {
-            "total": 394.0879952170071,
+            "total": 3527.804799097008,
             "count": 1,
-            "self": 0.6638770639838185,
+            "self": 5.41858486039564,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 4.369106300000567,
+                    "total": 2.0124125689908396,
                     "count": 1,
-                    "self": 4.369106300000567
+                    "self": 2.0124125689908396
                 },
                 "TrainerController.advance": {
-                    "total": 388.9300568620383,
-                    "count": 18206,
-                    "self": 0.33170540115679614,
+                    "total": 3520.259165747644,
+                    "count": 181874,
+                    "self": 2.6112302511755843,
                     "children": {
                         "env_step": {
-                            "total": 388.59835146088153,
-                            "count": 18206,
-                            "self": 279.28730860404903,
+                            "total": 3517.6479354964686,
+                            "count": 181874,
+                            "self": 2569.623420906806,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 109.011324763007,
-                                    "count": 18206,
-                                    "self": 1.6027072951255832,
+                                    "total": 945.3249118052481,
+                                    "count": 181874,
+                                    "self": 13.851257300615543,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 107.40861746788141,
-                                            "count": 18206,
-                                            "self": 14.976935813057935,
+                                            "total": 931.4736545046326,
+                                            "count": 181874,
+                                            "self": 127.77290135616204,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 92.43168165482348,
-                                                    "count": 18206,
-                                                    "self": 92.43168165482348
+                                                    "total": 803.7007531484705,
+                                                    "count": 181874,
+                                                    "self": 803.7007531484705
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.2997180938255042,
-                                    "count": 18206,
+                                    "total": 2.69960278441431,
+                                    "count": 181874,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 393.185588507622,
-                                            "count": 18206,
+                                            "total": 3521.14344334777,
+                                            "count": 181874,
                                             "is_parallel": true,
-                                            "self": 192.11333968420513,
+                                            "self": 1719.3351771153102,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -224,48 +224,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.00216466499841772,
+                                                            "total": 0.0019330479844938964,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006561369227711111,
+                                                            "self": 0.0005646030185744166,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.001508528075646609,
+                                                                    "total": 0.0013684449659194797,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.001508528075646609
+                                                                    "self": 0.0013684449659194797
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04352818301413208,
+                                                            "total": 0.048041015019407496,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00041333597619086504,
+                                                            "self": 0.00035946001298725605,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0003844230086542666,
+                                                                    "total": 0.0002662810147739947,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003844230086542666
+                                                                    "self": 0.0002662810147739947
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04146291600773111,
+                                                                    "total": 0.046154933981597424,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04146291600773111
+                                                                    "self": 0.046154933981597424
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.001267508021555841,
+                                                                    "total": 0.0012603400100488216,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003045150078833103,
+                                                                    "self": 0.00030130898812785745,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0009629930136725307,
+                                                                            "total": 0.0009590310219209641,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0009629930136725307
+                                                                            "self": 0.0009590310219209641
                                                                         }
                                                                     }
                                                                 }
@@ -274,34 +274,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 201.07224882341688,
-                                                    "count": 18205,
+                                                    "total": 1801.8082662324596,
+                                                    "count": 181873,
                                                     "is_parallel": true,
-                                                    "self": 7.351680302876048,
+                                                    "self": 66.5949679738842,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 4.4477454441657756,
-                                                            "count": 18205,
+                                                            "total": 41.4052872666507,
+                                                            "count": 181873,
                                                             "is_parallel": true,
-                                                            "self": 4.4477454441657756
+                                                            "self": 41.4052872666507
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 165.33834766363725,
-                                                            "count": 18205,
+                                                            "total": 1474.7900642491877,
+                                                            "count": 181873,
                                                             "is_parallel": true,
-                                                            "self": 165.33834766363725
+                                                            "self": 1474.7900642491877
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 23.93447541273781,
-                                                            "count": 18205,
+                                                            "total": 219.01794674273697,
+                                                            "count": 181873,
                                                             "is_parallel": true,
-                                                            "self": 5.489679446560331,
+                                                            "self": 50.45674358413089,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 18.44479596617748,
-                                                                    "count": 182050,
+                                                                    "total": 168.56120315860608,
+                                                                    "count": 1818730,
                                                                     "is_parallel": true,
-                                                                    "self": 18.44479596617748
+                                                                    "self": 168.56120315860608
                                                                 }
                                                             }
                                                         }
@@ -316,9 +316,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 0.00014378997730091214,
+                    "total": 0.0003306930011603981,
                     "count": 1,
-                    "self": 0.00014378997730091214,
+                    "self": 0.0003306930011603981,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -327,36 +327,36 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 386.4299365392362,
-                                    "count": 513537,
+                                    "total": 3502.2347593795857,
+                                    "count": 3965452,
                                     "is_parallel": true,
-                                    "self": 7.588924139650771,
+                                    "self": 56.153643384197494,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 206.30712276586564,
-                                            "count": 513537,
+                                            "total": 1823.7294392998156,
+                                            "count": 3965452,
                                             "is_parallel": true,
-                                            "self": 205.5930035088968,
+                                            "self": 1812.3949490989326,
                                             "children": {
                                                 "RLTrainer._checkpoint": {
-                                                    "total": 0.7141192569688428,
-                                                    "count": 4,
+                                                    "total": 11.33449020088301,
+                                                    "count": 40,
                                                     "is_parallel": true,
-                                                    "self": 0.7141192569688428
+                                                    "self": 11.33449020088301
                                                 }
                                             }
                                         },
                                         "_update_policy": {
-                                            "total": 172.5338896337198,
-                                            "count": 90,
+                                            "total": 1622.3516766955727,
+                                            "count": 909,
                                             "is_parallel": true,
-                                            "self": 50.95602535252692,
+                                            "self": 472.6568366049323,
                                             "children": {
                                                 "TorchPPOOptimizer.update": {
-                                                    "total": 121.57786428119289,
-                                                    "count": 4578,
+                                                    "total": 1149.6948400906404,
+                                                    "count": 46257,
                                                     "is_parallel": true,
-                                                    "self": 121.57786428119289
+                                                    "self": 1149.6948400906404
                                                 }
                                             }
                                         }
@@ -367,14 +367,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.12481120100710541,
+                    "total": 0.11430522697628476,
                     "count": 1,
-                    "self": 0.001185044995509088,
+                    "self": 0.000969816988799721,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.12362615601159632,
+                            "total": 0.11333540998748504,
                             "count": 1,
-                            "self": 0.12362615601159632
+                            "self": 0.11333540998748504
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,58 +2,103 @@
     "SnowballTarget": {
         "checkpoints": [
             {
-                "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 13.818181818181818,
-                "creation_time": 1673800127.8264518,
+                "steps": 1599976,
+                "file_path": "results/SnowballTarget5/SnowballTarget/SnowballTarget-1599976.onnx",
+                "reward": 27.727272727272727,
+                "creation_time": 1673826592.562898,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/SnowballTarget5/SnowballTarget/SnowballTarget-1599976.pt"
                 ]
             },
             {
-                "steps": 99960,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 20.181818181818183,
-                "creation_time": 1673800227.5947294,
+                "steps": 1649992,
+                "file_path": "results/SnowballTarget5/SnowballTarget/SnowballTarget-1649992.onnx",
+                "reward": 27.6,
+                "creation_time": 1673826675.4486237,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                    "results/SnowballTarget5/SnowballTarget/SnowballTarget-1649992.pt"
                 ]
             },
             {
-                "steps": 149984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 22.818181818181817,
-                "creation_time": 1673800327.2283962,
+                "steps": 1699936,
+                "file_path": "results/SnowballTarget5/SnowballTarget/SnowballTarget-1699936.onnx",
+                "reward": 27.545454545454547,
+                "creation_time": 1673826756.14448,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                    "results/SnowballTarget5/SnowballTarget/SnowballTarget-1699936.pt"
                 ]
             },
             {
-                "steps": 199984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 25.181818181818183,
-                "creation_time": 1673800417.1439798,
+                "steps": 1749960,
+                "file_path": "results/SnowballTarget5/SnowballTarget/SnowballTarget-1749960.onnx",
+                "reward": 28.181818181818183,
+                "creation_time": 1673826837.3941545,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                    "results/SnowballTarget5/SnowballTarget/SnowballTarget-1749960.pt"
                 ]
             },
             {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 25.181818181818183,
-                "creation_time": 1673800417.297236,
+                "steps": 1799984,
+                "file_path": "results/SnowballTarget5/SnowballTarget/SnowballTarget-1799984.onnx",
+                "reward": 28.0,
+                "creation_time": 1673826920.0776684,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/SnowballTarget5/SnowballTarget/SnowballTarget-1799984.pt"
+                ]
+            },
+            {
+                "steps": 1849984,
+                "file_path": "results/SnowballTarget5/SnowballTarget/SnowballTarget-1849984.onnx",
+                "reward": 28.181818181818183,
+                "creation_time": 1673827000.915594,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget5/SnowballTarget/SnowballTarget-1849984.pt"
+                ]
+            },
+            {
+                "steps": 1899944,
+                "file_path": "results/SnowballTarget5/SnowballTarget/SnowballTarget-1899944.onnx",
+                "reward": 28.272727272727273,
+                "creation_time": 1673827082.3755538,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget5/SnowballTarget/SnowballTarget-1899944.pt"
+                ]
+            },
+            {
+                "steps": 1949968,
+                "file_path": "results/SnowballTarget5/SnowballTarget/SnowballTarget-1949968.onnx",
+                "reward": 27.454545454545453,
+                "creation_time": 1673827165.5384333,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget5/SnowballTarget/SnowballTarget-1949968.pt"
+                ]
+            },
+            {
+                "steps": 1999992,
+                "file_path": "results/SnowballTarget5/SnowballTarget/SnowballTarget-1999992.onnx",
+                "reward": 28.454545454545453,
+                "creation_time": 1673827247.6539536,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget5/SnowballTarget/SnowballTarget-1999992.pt"
+                ]
+            },
+            {
+                "steps": 2000376,
+                "file_path": "results/SnowballTarget5/SnowballTarget/SnowballTarget-2000376.onnx",
+                "reward": 28.454545454545453,
+                "creation_time": 1673827247.8208814,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget5/SnowballTarget/SnowballTarget-2000376.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 200112,
-            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 25.181818181818183,
-            "creation_time": 1673800417.297236,
+            "steps": 2000376,
+            "file_path": "results/SnowballTarget5/SnowballTarget.onnx",
+            "reward": 28.454545454545453,
+            "creation_time": 1673827247.8208814,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                "results/SnowballTarget5/SnowballTarget/SnowballTarget-2000376.pt"
             ]
         }
     },