Normalized Run

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc3de42192c8f08f080991d16f4343ac9b7787f878c0e1b004a7ad1f6bbd0ec3
-size 650646
+oid sha256:dff31d1a9dae33f8d7fdb4e43056feb6b7b8f4e69344ea601823fccc4a239175
+size 657877

SnowballTarget/SnowballTarget-149984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc673050629ed2f37dc3f8dffdbc03bc0f2767f841643d35f3db6b98a9cbcc3e
-size 650646
+oid sha256:c9ace793dc7823dc18f2211c2c6656c0e267b6afff88680b85fa90b508651ffa
+size 657877

SnowballTarget/SnowballTarget-149984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30d753226611de4f140a5dfe2d7af8196ffb649ac17861ce4960c99682df6b16
-size 3850075
+oid sha256:88215ba936837c83c0fd274400f9fcff52946987a26b745ef5cbf19d8d76b5c5
+size 3872166

SnowballTarget/SnowballTarget-199984.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc3de42192c8f08f080991d16f4343ac9b7787f878c0e1b004a7ad1f6bbd0ec3
-size 650646
+oid sha256:932d31299e00121096af59dfb40ea0bc495fd2ecf1d0603b7f3ba663500aeaf0
+size 657877

SnowballTarget/SnowballTarget-199984.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c9fcb3773cc1496dbda0898e1d1ce13d503c57358cefcbdce4fce9ba30d4186
-size 3850075
+oid sha256:40e9e13d62cf39229cbca9972604c3f6baf3d638a484d94fe7a03ace4ae868fd
+size 3872166

SnowballTarget/SnowballTarget-200112.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc3de42192c8f08f080991d16f4343ac9b7787f878c0e1b004a7ad1f6bbd0ec3
-size 650646
+oid sha256:dff31d1a9dae33f8d7fdb4e43056feb6b7b8f4e69344ea601823fccc4a239175
+size 657877

SnowballTarget/SnowballTarget-200112.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53f18d5b07994efb2217e7049b8989ab3cdbee96313371817ff31e0348e2da05
-size 3850075
+oid sha256:413b4d9f34fa051d13d17d1905466fed54cde7d0d9d955d38dfde4bb5ae558a6
+size 3872166

SnowballTarget/SnowballTarget-49936.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd99d0a82e0b8bf932115707eb11b1b777878fe92073e9814e33b9460eb0ae9b
-size 650646
+oid sha256:34e7ec35b7892945b0849c49b2e6bbfb0de1b2b75747b844e256f7283aa44140
+size 657877

SnowballTarget/SnowballTarget-49936.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe350c5a1eceae6d99d8d881beb7c78071d2045253909a87234606b0ecdd7b9f
-size 3850000
+oid sha256:bf268771ed2fc45414d6b6e3699d76579c22ebd5a4fdcc20465c3bab69cc6695
+size 3872061

SnowballTarget/SnowballTarget-99960.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b99c35b770d4aaacbdd1bd1dabe9fe5b2e5aae3b897d9821f9816207a118198
-size 650646
+oid sha256:9decb9da9c41d00433a86f15a5cc10e4756c27f8533fe1e0c16253f64b116dfd
+size 657877

SnowballTarget/SnowballTarget-99960.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06f2f96efd0da362fe030fee53436d507daa974a0984fc79ae814e23243847ea
-size 3850000
+oid sha256:c499fe648c1f07c02ab98fa98b74a277a60f7f69abc089fe246c7983b7856cdd
+size 3872061

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc72e9f955f72e4ca656cd455fc3dde438649fff9fea23b556de2438b187615a
-size 3849250
+oid sha256:1f4510e24e0a269c60f90ede68efafb1d70f3b6a35ea7214060dc4b439fb2650
+size 3871011

SnowballTarget/events.out.tfevents.1704660108.e75356f8ccbc.14719.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdd38602d00f146388475ef54db5d81abd2800c46525cd00cb6ae90cfadf68e8
+size 23539

config.json

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

@@ -16,7 +16,7 @@ behaviors:
       epsilon_schedule: linear
     checkpoint_interval: 50000
     network_settings:
-      normalize: false
+      normalize: true
       hidden_units: 256
       num_layers: 2
       vis_encode_type: simple
@@ -66,10 +66,10 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: SnowballTarget1
+  run_id: SnowballTargetNorm
   initialize_from: null
   load_model: false
-  resume: true
+  resume: false
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -31,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.127 seconds
+- Completed reload, in  0.085 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -42,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.860521 ms
+UnloadTime: 0.668313 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.
@@ -50,7 +50,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames
+      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
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -78,7 +78,7 @@ Memory Statistics:
     [ALLOC_TEMP_Job.Worker 0]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 2.8 KB
+      Peak Allocated Bytes 3.6 KB
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 10]
       Initial Block Size 32.0 KB
@@ -166,22 +166,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 3
+  Peak main deferred allocation count 37
     [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]: 1 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 5462 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 4.6 MB
+      Peak Allocated memory 6.7 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 1 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 5462 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.7 MB
+      Peak Allocated memory 17.8 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -195,7 +195,7 @@ Memory Statistics:
   Overflow Count (full) 0
 [ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
   Initial Block Size 2.0 MB
-  Used Block Count 1
+  Used Block Count 2
   Overflow Count (too large) 0
   Overflow Count (full) 0
 [ALLOC_TEMP_JOB_ASYNC (Background)]
@@ -210,13 +210,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5196 frames, [64.0 KB-128.0 KB]: 266 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 65.6 KB
+      Peak Allocated memory 66.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5462 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -228,13 +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]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5462 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
-      Peak Allocated memory 0.5 MB
+      Peak Allocated memory 0.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5461 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
@@ -246,13 +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]: 1 frames
+      Peak usage frame count: [0-1.0 KB]: 5462 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]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 5462 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -1,40 +1,317 @@
 {
     "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 1.127758264541626,
+            "min": 1.127758264541626,
+            "max": 2.8530564308166504,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 10817.45703125,
+            "min": 10817.45703125,
+            "max": 29343.685546875,
+            "count": 20
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 199984.0,
+            "min": 9952.0,
+            "max": 199984.0,
+            "count": 20
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 199984.0,
+            "min": 9952.0,
+            "max": 199984.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 13.342976570129395,
+            "min": 0.42259612679481506,
+            "max": 13.342976570129395,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 2601.88037109375,
+            "min": 81.98365020751953,
+            "max": 2732.46337890625,
+            "count": 20
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 20
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 10945.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06675720262151742,
+            "min": 0.06254128525184818,
+            "max": 0.07492010378118245,
+            "count": 20
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.2670288104860697,
+            "min": 0.25923942435788466,
+            "max": 0.3672333581498071,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.20792854131728997,
+            "min": 0.14113803842451936,
+            "max": 0.3251086139649737,
+            "count": 20
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.8317141652691599,
+            "min": 0.5645521536980774,
+            "max": 1.391468170318095,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 8.082097306000005e-06,
+            "min": 8.082097306000005e-06,
+            "max": 0.000291882002706,
+            "count": 20
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 3.232838922400002e-05,
+            "min": 3.232838922400002e-05,
+            "max": 0.00138516003828,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10269400000000001,
+            "min": 0.10269400000000001,
+            "max": 0.19729400000000002,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.41077600000000003,
+            "min": 0.41077600000000003,
+            "max": 0.96172,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.0001444306000000001,
+            "min": 0.0001444306000000001,
+            "max": 0.0048649706,
+            "count": 20
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0005777224000000004,
+            "min": 0.0005777224000000004,
+            "max": 0.023089828,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 26.045454545454547,
+            "min": 3.840909090909091,
+            "max": 26.381818181818183,
+            "count": 20
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 1146.0,
+            "min": 169.0,
+            "max": 1451.0,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 26.045454545454547,
+            "min": 3.840909090909091,
+            "max": 26.381818181818183,
+            "count": 20
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 1146.0,
+            "min": 169.0,
+            "max": 1451.0,
+            "count": 20
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 20
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 20
+        }
+    },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1704659582",
+        "start_time_seconds": "1704660107",
         "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTargetNorm --no-graphics",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.1.2+cu121",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1704659585"
+        "end_time_seconds": "1704660577"
     },
-    "total": 3.5388320080000994,
+    "total": 470.01215595999975,
     "count": 1,
-    "self": 0.48761477199968795,
+    "self": 0.43350531499982026,
     "children": {
         "run_training.setup": {
-            "total": 0.07632201900014479,
+            "total": 0.04527551299997867,
             "count": 1,
-            "self": 0.07632201900014479
+            "self": 0.04527551299997867
         },
         "TrainerController.start_learning": {
-            "total": 2.9748952170002667,
+            "total": 469.53337513199995,
             "count": 1,
-            "self": 0.000329594000504585,
+            "self": 0.5289272990198697,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.61186405799981,
+                    "total": 1.8444162490000053,
                     "count": 1,
-                    "self": 2.61186405799981
+                    "self": 1.8444162490000053
+                },
+                "TrainerController.advance": {
+                    "total": 467.0387818119798,
+                    "count": 18205,
+                    "self": 0.2606715079609785,
+                    "children": {
+                        "env_step": {
+                            "total": 466.7781103040188,
+                            "count": 18205,
+                            "self": 298.0949224399783,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 168.3995507679847,
+                                    "count": 18205,
+                                    "self": 1.5081894449931497,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 166.89136132299154,
+                                            "count": 18205,
+                                            "self": 166.89136132299154
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.283637096055827,
+                                    "count": 18205,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 468.2429345689852,
+                                            "count": 18205,
+                                            "is_parallel": true,
+                                            "self": 244.73288004601045,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.002579008999873622,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0007307010009753867,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0018483079988982354,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0018483079988982354
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.03680281000015384,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.000644504000320012,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00043893499969271943,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00043893499969271943
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.03350800899988826,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.03350800899988826
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.002211362000252848,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003915690012945561,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0018197929989582917,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0018197929989582917
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 223.51005452297477,
+                                                    "count": 18204,
+                                                    "is_parallel": true,
+                                                    "self": 10.437711326947465,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 5.1885859980120586,
+                                                            "count": 18204,
+                                                            "is_parallel": true,
+                                                            "self": 5.1885859980120586
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 171.53052284798878,
+                                                            "count": 18204,
+                                                            "is_parallel": true,
+                                                            "self": 171.53052284798878
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 36.35323435002647,
+                                                            "count": 18204,
+                                                            "is_parallel": true,
+                                                            "self": 6.579203484086975,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 29.774030865939494,
+                                                                    "count": 182040,
+                                                                    "is_parallel": true,
+                                                                    "self": 29.774030865939494
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
                 },
                 "trainer_threads": {
-                    "total": 2.284700030941167e-05,
+                    "total": 0.0001214310000250407,
                     "count": 1,
-                    "self": 2.284700030941167e-05,
+                    "self": 0.0001214310000250407,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -43,16 +320,38 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 0.00021595699990939465,
-                                    "count": 1,
+                                    "total": 461.94796281602976,
+                                    "count": 621226,
                                     "is_parallel": true,
-                                    "self": 2.1705000108340755e-05,
+                                    "self": 12.779857648179586,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 0.0001942519998010539,
-                                            "count": 1,
+                                            "total": 261.2980096818501,
+                                            "count": 621226,
+                                            "is_parallel": true,
+                                            "self": 260.4070634278505,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 0.890946253999573,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 0.890946253999573
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 187.87009548600008,
+                                            "count": 90,
                                             "is_parallel": true,
-                                            "self": 0.0001942519998010539
+                                            "self": 67.42968477998602,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 120.44041070601406,
+                                                    "count": 4587,
+                                                    "is_parallel": true,
+                                                    "self": 120.44041070601406
+                                                }
+                                            }
                                         }
                                     }
                                 }
@@ -61,14 +360,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.3626787179996427,
+                    "total": 0.12112834100025793,
                     "count": 1,
-                    "self": 0.0013108799998917675,
+                    "self": 0.0012934460000906256,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.3613678379997509,
+                            "total": 0.11983489500016731,
                             "count": 1,
-                            "self": 0.3613678379997509
+                            "self": 0.11983489500016731
                         }
                     }
                 }

run_logs/training_status.json

@@ -3,66 +3,57 @@
         "checkpoints": [
             {
                 "steps": 49936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
-                "reward": 14.636363636363637,
-                "creation_time": 1704659009.7005053,
+                "file_path": "results/SnowballTargetNorm/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 16.727272727272727,
+                "creation_time": 1704660228.8272896,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                    "results/SnowballTargetNorm/SnowballTarget/SnowballTarget-49936.pt"
                 ]
             },
             {
                 "steps": 99960,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.onnx",
-                "reward": 19.90909090909091,
-                "creation_time": 1704659122.246906,
+                "file_path": "results/SnowballTargetNorm/SnowballTarget/SnowballTarget-99960.onnx",
+                "reward": 24.818181818181817,
+                "creation_time": 1704660345.7188063,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-99960.pt"
+                    "results/SnowballTargetNorm/SnowballTarget/SnowballTarget-99960.pt"
                 ]
             },
             {
                 "steps": 149984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 22.454545454545453,
-                "creation_time": 1704659237.0889947,
+                "file_path": "results/SnowballTargetNorm/SnowballTarget/SnowballTarget-149984.onnx",
+                "reward": 26.727272727272727,
+                "creation_time": 1704660461.5814161,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                    "results/SnowballTargetNorm/SnowballTarget/SnowballTarget-149984.pt"
                 ]
             },
             {
                 "steps": 199984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.onnx",
-                "reward": 24.09090909090909,
-                "creation_time": 1704659346.513504,
+                "file_path": "results/SnowballTargetNorm/SnowballTarget/SnowballTarget-199984.onnx",
+                "reward": 26.272727272727273,
+                "creation_time": 1704660576.865563,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199984.pt"
+                    "results/SnowballTargetNorm/SnowballTarget/SnowballTarget-199984.pt"
                 ]
             },
             {
                 "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 24.09090909090909,
-                "creation_time": 1704659346.627961,
+                "file_path": "results/SnowballTargetNorm/SnowballTarget/SnowballTarget-200112.onnx",
+                "reward": 26.272727272727273,
+                "creation_time": 1704660577.0134676,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
-                ]
-            },
-            {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": null,
-                "creation_time": 1704659585.1354163,
-                "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/SnowballTargetNorm/SnowballTarget/SnowballTarget-200112.pt"
                 ]
             }
         ],
         "final_checkpoint": {
             "steps": 200112,
-            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": null,
-            "creation_time": 1704659585.1354163,
+            "file_path": "results/SnowballTargetNorm/SnowballTarget.onnx",
+            "reward": 26.272727272727273,
+            "creation_time": 1704660577.0134676,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                "results/SnowballTargetNorm/SnowballTarget/SnowballTarget-200112.pt"
             ]
         }
     },