500K Step Trainning Agent

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e059fbb82d6d65682070582fe57e21d79692a2eb236dafe47590c915842d97bb
+oid sha256:96c772ece7f9a40adee40b2e8b5040ba9de26d3ba9c267bce33ec274c63e1a75
 size 646532

SnowballTarget/{SnowballTarget-149984.onnx → SnowballTarget-249984.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa68ac8f2f4758d9e81a993ba1e65a814a03575e2c5b0c372f7261130951809e
+oid sha256:b20fd838dce7ccc00ecebb325bfe4dc8d2fd50aa9757727bf606b14e332fe16f
 size 646532

SnowballTarget/{SnowballTarget-99960.pt → SnowballTarget-249984.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e65fdc8f305e4e52e0629727338f19104ad33e3d0cea40618a79de85b8d21ea
+oid sha256:8bd196c59bfcaf10abdce372602c80e34807aa6105d25366d3ea086d99c0dcc3
 size 3843968

SnowballTarget/{SnowballTarget-99960.onnx → SnowballTarget-299944.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a219b4751c8b3666c5ffd16021b23750330e5b89c1302c76cd5133000107cf23
+oid sha256:17a2a116ac1b4180e88392dc7c247e19c5bd35edd82e25a514a4e5269a101dfc
 size 646532

SnowballTarget/{SnowballTarget-149984.pt → SnowballTarget-299944.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a16b977bd2ff2478e32b096dabfdd0e21f96e3368dc3ebceb42e7258c96d3f59
+oid sha256:b90e748bafd7c33e61b86715ee036af952f4aab9011c227d79a280eedd25affb
 size 3843968

SnowballTarget/{SnowballTarget-49936.onnx → SnowballTarget-349968.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a87b5314ad5661b1fafd0ae2b517fa42f4f2e09376c97a64c8b48a53d55ff37
+oid sha256:fe94ba2022928a9a447112989963c9b4109dabe655bdf29d2be90ced1748aaf9
 size 646532

SnowballTarget/{SnowballTarget-49936.pt → SnowballTarget-349968.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63fe7551bd6242c77d954d699b6d4de1340e8ce66fa45ecb6a7f1d4e37b42c28
+oid sha256:94782d445a7841fc969622976517e07f35f5678b2fcb1d80759a438bf189ee01
 size 3843968

SnowballTarget/SnowballTarget-399968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c86a00fdcd77fb128b3cd1cedef1bd5f105aeaf03d7a4e83d08093f25994ce8
+size 646532

SnowballTarget/SnowballTarget-399968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49c2114a94c41e86c4588bb71a5dbcdce200fe718221373079efa003268f79ff
+size 3843968

SnowballTarget/SnowballTarget-449992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f51b5577ab81a166da9030a3bcef0bde6867d2ca47650c2eec50b7919ad01755
+size 646532

SnowballTarget/SnowballTarget-449992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dd3ca2d4b34d8af8253fb45c32dc9d605e3ab062271306dba009a44de5ddaff
+size 3843968

SnowballTarget/SnowballTarget-499952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96c772ece7f9a40adee40b2e8b5040ba9de26d3ba9c267bce33ec274c63e1a75
+size 646532

SnowballTarget/SnowballTarget-499952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19a2fc614bf1cf2476730424c3a93a8dfe640e2d40a9e9101e5d26d96d635ec4
+size 3843968

SnowballTarget/SnowballTarget-500016.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96c772ece7f9a40adee40b2e8b5040ba9de26d3ba9c267bce33ec274c63e1a75
+size 646532

SnowballTarget/SnowballTarget-500016.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c0ebbf2f7707aef1728f0e45066d410bc2ffbe741a2d52a1225754ea3c58a15
+size 3843968

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77154e5e1280e87d4479860e435a180c030e691119279c7ef73cf327a934a081
+oid sha256:0c0ebbf2f7707aef1728f0e45066d410bc2ffbe741a2d52a1225754ea3c58a15
 size 3843968

SnowballTarget/events.out.tfevents.1682358087.a18477c96443.5751.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:414b7e33997e9b6aa564d7e77ba721352b775084f56c6c9673df128af78ce82f
+size 1114

SnowballTarget/events.out.tfevents.1682358145.a18477c96443.6061.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b6283f3782d217de82e84cc41740ace910c697bb93a19d1fb24b9656dd01a0b
+size 25806

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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": 0.0003, "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": 500000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -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: true
@@ -67,7 +67,7 @@ checkpoint_settings:
   run_id: SnowballTarget1
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
 Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
-Unable to load player prefs
 Initialize engine version: 2021.3.14f1 (eee1884e7226)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.132 seconds
+- Completed reload, in  0.088 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -45,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 1.010365 ms
+UnloadTime: 0.761045 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -53,7 +50,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 5368 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]: 8047 frames, [16.0 KB-32.0 KB]: 136 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -169,19 +166,19 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 40
+  Peak main deferred allocation count 36
     [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]: 5460 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 8184 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 6.6 MB
+      Peak Allocated memory 7.3 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 5460 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 8184 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 17.8 MB
@@ -213,13 +210,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 4218 frames, [64.0 KB-128.0 KB]: 1242 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 7212 frames, [64.0 KB-128.0 KB]: 972 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 66.8 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 5460 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 8184 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -231,13 +228,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 5460 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 8184 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]: 5459 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 8183 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 MB
@@ -249,13 +246,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 5460 frames
+      Peak usage frame count: [0-1.0 KB]: 8184 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]: 5460 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 8184 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": 0.9684804677963257,
-            "min": 0.9665554165840149,
-            "max": 2.8610684871673584,
-            "count": 20
+            "value": 0.6655184626579285,
+            "min": 0.617180585861206,
+            "max": 0.9582071900367737,
+            "count": 30
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 9247.0517578125,
-            "min": 9247.0517578125,
-            "max": 29331.673828125,
-            "count": 20
+            "value": 6420.2568359375,
+            "min": 5858.89501953125,
+            "max": 9813.0,
+            "count": 30
         },
         "SnowballTarget.Step.mean": {
-            "value": 199984.0,
-            "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+            "value": 499952.0,
+            "min": 209936.0,
+            "max": 499952.0,
+            "count": 30
         },
         "SnowballTarget.Step.sum": {
-            "value": 199984.0,
-            "min": 9952.0,
-            "max": 199984.0,
-            "count": 20
+            "value": 499952.0,
+            "min": 209936.0,
+            "max": 499952.0,
+            "count": 30
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 11.88376235961914,
-            "min": 0.42129021883010864,
-            "max": 11.88376235961914,
-            "count": 20
+            "value": 13.066350936889648,
+            "min": 11.845895767211914,
+            "max": 13.117155075073242,
+            "count": 30
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2317.333740234375,
-            "min": 81.73030090332031,
-            "max": 2420.123046875,
-            "count": 20
+            "value": 2665.53564453125,
+            "min": 2291.858642578125,
+            "max": 2673.39697265625,
+            "count": 30
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
             "value": 199.0,
             "min": 199.0,
             "max": 199.0,
-            "count": 20
+            "count": 30
         },
         "SnowballTarget.Environment.EpisodeLength.sum": {
-            "value": 8756.0,
+            "value": 10945.0,
             "min": 8756.0,
             "max": 10945.0,
-            "count": 20
+            "count": 30
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.06678682855386332,
-            "min": 0.06264865814648823,
-            "max": 0.07348273087785963,
-            "count": 20
+            "value": 0.06782656824045048,
+            "min": 0.061637699475635174,
+            "max": 0.07558078284441852,
+            "count": 30
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.2671473142154533,
-            "min": 0.25059463258595294,
-            "max": 0.35259857336573347,
-            "count": 20
+            "value": 0.3391328412022524,
+            "min": 0.2465507979025407,
+            "max": 0.3779039142220926,
+            "count": 30
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.18828831204012328,
-            "min": 0.12193425533854788,
-            "max": 0.2692366852333733,
-            "count": 20
+            "value": 0.16957302873625474,
+            "min": 0.15925985475381216,
+            "max": 0.19927547601800338,
+            "count": 30
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.7531532481604931,
-            "min": 0.4877370213541915,
-            "max": 1.3165682127662732,
-            "count": 20
+            "value": 0.8478651436812737,
+            "min": 0.6766528339654792,
+            "max": 0.9778521423246346,
+            "count": 30
         },
         "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 8.082097306000005e-06,
-            "min": 8.082097306000005e-06,
-            "max": 0.000291882002706,
-            "count": 20
+            "value": 3.1056989647999945e-06,
+            "min": 3.1056989647999945e-06,
+            "max": 0.00017668564110480002,
+            "count": 30
         },
         "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 3.232838922400002e-05,
-            "min": 3.232838922400002e-05,
-            "max": 0.00138516003828,
-            "count": 20
+            "value": 1.5528494823999972e-05,
+            "min": 1.5528494823999972e-05,
+            "max": 0.000853728215424,
+            "count": 30
         },
         "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10269400000000001,
-            "min": 0.10269400000000001,
-            "max": 0.19729400000000002,
-            "count": 20
+            "value": 0.10103520000000002,
+            "min": 0.10103520000000002,
+            "max": 0.15889520000000001,
+            "count": 30
         },
         "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.41077600000000003,
-            "min": 0.41077600000000003,
-            "max": 0.96172,
-            "count": 20
+            "value": 0.5051760000000001,
+            "min": 0.4120608,
+            "max": 0.7845760000000002,
+            "count": 30
         },
         "SnowballTarget.Policy.Beta.mean": {
-            "value": 0.0001444306000000001,
-            "min": 0.0001444306000000001,
-            "max": 0.0048649706,
-            "count": 20
+            "value": 6.165647999999992e-05,
+            "min": 6.165647999999992e-05,
+            "max": 0.002948870480000001,
+            "count": 30
         },
         "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.0005777224000000004,
-            "min": 0.0005777224000000004,
-            "max": 0.023089828,
-            "count": 20
+            "value": 0.0003082823999999996,
+            "min": 0.0003082823999999996,
+            "max": 0.0142503424,
+            "count": 30
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 23.34090909090909,
-            "min": 3.5,
-            "max": 23.436363636363637,
-            "count": 20
+            "value": 26.01818181818182,
+            "min": 23.272727272727273,
+            "max": 26.01818181818182,
+            "count": 30
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 1027.0,
-            "min": 154.0,
-            "max": 1289.0,
-            "count": 20
+            "value": 1431.0,
+            "min": 1033.0,
+            "max": 1431.0,
+            "count": 30
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 23.34090909090909,
-            "min": 3.5,
-            "max": 23.436363636363637,
-            "count": 20
+            "value": 26.01818181818182,
+            "min": 23.272727272727273,
+            "max": 26.01818181818182,
+            "count": 30
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 1027.0,
-            "min": 154.0,
-            "max": 1289.0,
-            "count": 20
+            "value": 1431.0,
+            "min": 1033.0,
+            "max": 1431.0,
+            "count": 30
         },
         "SnowballTarget.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 30
         },
         "SnowballTarget.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 20
+            "count": 30
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1682357155",
+        "start_time_seconds": "1682358144",
         "python_version": "3.9.16 (main, Dec  7 2022, 01:11:51) \n[GCC 9.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
         "mlagents_version": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1682357672"
+        "end_time_seconds": "1682358916"
     },
-    "total": 516.7167141909999,
+    "total": 771.782464225,
     "count": 1,
-    "self": 0.48507005299984485,
+    "self": 0.42619025900012275,
     "children": {
         "run_training.setup": {
-            "total": 0.20040222800002994,
+            "total": 0.12090538699999342,
             "count": 1,
-            "self": 0.20040222800002994
+            "self": 0.12090538699999342
         },
         "TrainerController.start_learning": {
-            "total": 516.0312419100001,
+            "total": 771.2353685789999,
             "count": 1,
-            "self": 0.6946911010028316,
+            "self": 0.9749921189966244,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 6.026232261000018,
+                    "total": 3.78697043499983,
                     "count": 1,
-                    "self": 6.026232261000018
+                    "self": 3.78697043499983
                 },
                 "TrainerController.advance": {
-                    "total": 509.17044381799707,
-                    "count": 18200,
-                    "self": 0.36501226900202255,
+                    "total": 766.3194630150033,
+                    "count": 27277,
+                    "self": 0.4873033090048011,
                     "children": {
                         "env_step": {
-                            "total": 508.80543154899505,
-                            "count": 18200,
-                            "self": 372.9479452349953,
+                            "total": 765.8321597059985,
+                            "count": 27277,
+                            "self": 560.3379320839692,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 135.518353045999,
-                                    "count": 18200,
-                                    "self": 1.9585550909902736,
+                                    "total": 205.00281449902013,
+                                    "count": 27277,
+                                    "self": 2.854428264005719,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 133.55979795500872,
-                                            "count": 18200,
-                                            "self": 133.55979795500872
+                                            "total": 202.1483862350144,
+                                            "count": 27277,
+                                            "self": 202.1483862350144
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.33913326800075083,
-                                    "count": 18200,
+                                    "total": 0.4914131230091243,
+                                    "count": 27277,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 514.3362900880015,
-                                            "count": 18200,
+                                            "total": 768.7621924489877,
+                                            "count": 27277,
                                             "is_parallel": true,
-                                            "self": 233.94241602600715,
+                                            "self": 348.3900992389922,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.006583159000001615,
+                                                            "total": 0.0020266750000246248,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0042210009999053,
+                                                            "self": 0.000663230999634834,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.002362158000096315,
+                                                                    "total": 0.0013634440003897907,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.002362158000096315
+                                                                    "self": 0.0013634440003897907
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.03869263500001807,
+                                                            "total": 0.03653779000001123,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006917510000334914,
+                                                            "self": 0.000623500000074273,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0003822740000032354,
+                                                                    "total": 0.00035205000017413113,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003822740000032354
+                                                                    "self": 0.00035205000017413113
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.03551086900000655,
+                                                                    "total": 0.033465286999899035,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.03551086900000655
+                                                                    "self": 0.033465286999899035
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0021077409999747942,
+                                                                    "total": 0.002096952999863788,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00041510799997013237,
+                                                                    "self": 0.00044193199937581085,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0016926330000046619,
+                                                                            "total": 0.0016550210004879773,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0016926330000046619
+                                                                            "self": 0.0016550210004879773
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 280.3938740619944,
-                                                    "count": 18199,
+                                                    "total": 420.37209320999546,
+                                                    "count": 27276,
                                                     "is_parallel": true,
-                                                    "self": 11.282627253996395,
+                                                    "self": 16.572916214011002,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 5.999943185995505,
-                                                            "count": 18199,
+                                                            "total": 9.062697829995159,
+                                                            "count": 27276,
                                                             "is_parallel": true,
-                                                            "self": 5.999943185995505
+                                                            "self": 9.062697829995159
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 227.30850375700072,
-                                                            "count": 18199,
+                                                            "total": 341.0861296830112,
+                                                            "count": 27276,
                                                             "is_parallel": true,
-                                                            "self": 227.30850375700072
+                                                            "self": 341.0861296830112
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 35.80279986500176,
-                                                            "count": 18199,
+                                                            "total": 53.65034948297807,
+                                                            "count": 27276,
                                                             "is_parallel": true,
-                                                            "self": 7.392354915014039,
+                                                            "self": 11.027815503917736,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 28.41044494998772,
-                                                                    "count": 181990,
+                                                                    "total": 42.622533979060336,
+                                                                    "count": 272760,
                                                                     "is_parallel": true,
-                                                                    "self": 28.41044494998772
+                                                                    "self": 42.622533979060336
                                                                 }
                                                             }
                                                         }
@@ -309,9 +309,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 3.7070000075800635e-05,
+                    "total": 6.132499993327656e-05,
                     "count": 1,
-                    "self": 3.7070000075800635e-05,
+                    "self": 6.132499993327656e-05,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -320,36 +320,36 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 504.75749249595043,
-                                    "count": 469320,
+                                    "total": 760.2009560629922,
+                                    "count": 695956,
                                     "is_parallel": true,
-                                    "self": 12.290094086947477,
+                                    "self": 18.176444329957803,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 281.2713377250029,
-                                            "count": 469320,
+                                            "total": 419.70010413003524,
+                                            "count": 695956,
                                             "is_parallel": true,
-                                            "self": 280.0705311930031,
+                                            "self": 417.8537270100355,
                                             "children": {
                                                 "RLTrainer._checkpoint": {
-                                                    "total": 1.200806531999831,
-                                                    "count": 4,
+                                                    "total": 1.8463771199997154,
+                                                    "count": 6,
                                                     "is_parallel": true,
-                                                    "self": 1.200806531999831
+                                                    "self": 1.8463771199997154
                                                 }
                                             }
                                         },
                                         "_update_policy": {
-                                            "total": 211.19606068400003,
-                                            "count": 90,
+                                            "total": 322.32440760299914,
+                                            "count": 136,
                                             "is_parallel": true,
-                                            "self": 75.00589306599863,
+                                            "self": 115.05255194398,
                                             "children": {
                                                 "TorchPPOOptimizer.update": {
-                                                    "total": 136.1901676180014,
-                                                    "count": 4587,
+                                                    "total": 207.27185565901914,
+                                                    "count": 6930,
                                                     "is_parallel": true,
-                                                    "self": 136.1901676180014
+                                                    "self": 207.27185565901914
                                                 }
                                             }
                                         }
@@ -360,14 +360,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.13983766000001197,
+                    "total": 0.15388168500021493,
                     "count": 1,
-                    "self": 0.0010233990000187987,
+                    "self": 0.002220347000275069,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.13881426099999317,
+                            "total": 0.15166133799993986,
                             "count": 1,
-                            "self": 0.13881426099999317
+                            "self": 0.15166133799993986
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,58 +2,103 @@
     "SnowballTarget": {
         "checkpoints": [
             {
-                "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 13.363636363636363,
-                "creation_time": 1682357288.7593153,
+                "steps": 199984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 22.363636363636363,
+                "creation_time": 1682357671.458759,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
                 ]
             },
             {
-                "steps": 99960,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 20.0,
-                "creation_time": 1682357417.0077095,
+                "steps": 200112,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 22.363636363636363,
+                "creation_time": 1682357671.6289852,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
                 ]
             },
             {
-                "steps": 149984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 21.90909090909091,
-                "creation_time": 1682357545.581245,
+                "steps": 200112,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": null,
+                "creation_time": 1682358091.1392028,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
                 ]
             },
             {
-                "steps": 199984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 22.363636363636363,
-                "creation_time": 1682357671.458759,
+                "steps": 249984,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.onnx",
+                "reward": 24.0,
+                "creation_time": 1682358278.3226972,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-249984.pt"
                 ]
             },
             {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 22.363636363636363,
-                "creation_time": 1682357671.6289852,
+                "steps": 299944,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-299944.onnx",
+                "reward": 24.363636363636363,
+                "creation_time": 1682358406.4953222,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-299944.pt"
+                ]
+            },
+            {
+                "steps": 349968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-349968.onnx",
+                "reward": 25.454545454545453,
+                "creation_time": 1682358535.671669,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-349968.pt"
+                ]
+            },
+            {
+                "steps": 399968,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.onnx",
+                "reward": 24.181818181818183,
+                "creation_time": 1682358665.1557727,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-399968.pt"
+                ]
+            },
+            {
+                "steps": 449992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-449992.onnx",
+                "reward": 24.727272727272727,
+                "creation_time": 1682358791.0211678,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-449992.pt"
+                ]
+            },
+            {
+                "steps": 499952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-499952.onnx",
+                "reward": 26.90909090909091,
+                "creation_time": 1682358915.5257006,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-499952.pt"
+                ]
+            },
+            {
+                "steps": 500016,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-500016.onnx",
+                "reward": 26.90909090909091,
+                "creation_time": 1682358915.7000394,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-500016.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 200112,
+            "steps": 500016,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 22.363636363636363,
-            "creation_time": 1682357671.6289852,
+            "reward": 26.90909090909091,
+            "creation_time": 1682358915.7000394,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-500016.pt"
             ]
         }
     },