Curiosity reward signal enabled

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e442260048cb1fd0580820e8e71b6cd24da625735e831be978b58d9b0be3e9f0
+oid sha256:64c7a453877b3eb4c12f616844f8e08e5e8226b2bfc1cde00e88151d80b1106f
 size 260484

SnowballTarget/SnowballTarget-305800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d17d39a84e454db3efe81d4c32ada1b2c401d78689c44c7d7d90f12fb8e6c95
+size 260484

SnowballTarget/SnowballTarget-305800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3edbfdcc94fd4cb187fe120b83176fde9ef55cf0220ad927b35d1da7c53fabb
+size 1180480

SnowballTarget/SnowballTarget-319960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d039d15074c8128323e918f4fbff0eb3c1671f6887e512c24058c16943646dc
+size 260484

SnowballTarget/SnowballTarget-319960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e63079e6bb0afda5f0a2a5f2375b8bd979ba0fc87c01033615d2e0fdaafb4e1f
+size 1588526

SnowballTarget/SnowballTarget-329992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44085ac39a3f14642bea44edcf63f33a494837312ae29c69679de02c9ac35c7
+size 260484

SnowballTarget/SnowballTarget-329992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8763104429c14d6931fbe1577b6b6299f01d8d795f3c2757eb9b34558be9fcf0
+size 1588526

SnowballTarget/SnowballTarget-339952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91556e78bcc74f88dec1ca15848a501005b8db8c51cf923e32371968f384d3c1
+size 260484

SnowballTarget/SnowballTarget-339952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57907b60675be8ad7daf0d3d611d15803d04bb673adca06b2947ef1c0a441bad
+size 1588526

SnowballTarget/SnowballTarget-349992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e070605cad6d71c2108a2aa88fa48af92b9cf61d9c68a4be4d84774a8fe05350
+size 260484

SnowballTarget/SnowballTarget-349992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b3ce24e7d49cd2fa8e03cf5fd159f0d86ce39c84be825a8d9800233c02c2004
+size 1588526

SnowballTarget/SnowballTarget-359944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d42f97a0cc2bbad5d66ad40f7512057f7214ac338fb4fcf2e6809c96a6eb8db
+size 260484

SnowballTarget/SnowballTarget-359944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b50a7df71542a34e674dbfbf844d21e93ec618984bb61cd7a09ba066b513856
+size 1588526

SnowballTarget/SnowballTarget-369984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45dfe1d9dd1523caa78c61cda134b7fe06a0f350dfdc11ec289d15cbb54f7dd2
+size 260484

SnowballTarget/SnowballTarget-369984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11a1e94523bcfd2c00828085ffa39f6b9a48ed46dc6725842aecf1161681576a
+size 1588526

SnowballTarget/SnowballTarget-379936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60ee4b2cb2da3b2df717a7cbd05c64608e149f133cd01cf7ec8a67ac885b20b0
+size 260484

SnowballTarget/SnowballTarget-379936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffa8a61cdbef68f9ac33f29be9e747588418d028181b01be315124c045ebbe5c
+size 1588526

SnowballTarget/SnowballTarget-382800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8a54147b2b41e80a384c1054be64832c6ac3ed9f3f3d734c0bffec933e17ed2
+size 260484

SnowballTarget/SnowballTarget-382800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adfe362c5653a6f3eef7eb245392dc61c8b5bc060fa2ce0956e99028d458074a
+size 990656

SnowballTarget/SnowballTarget-389976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34004c5be2562e958bdcd9f205b0df0f9ea8902dcdbcf0bc3e6aec2c2eaeae09
+size 260484

SnowballTarget/SnowballTarget-389976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:219834d71bef8d1a7aeee375c46228b8f4e1d827f1dbe8bd099ee4ca5f75d6f6
+size 1588526

SnowballTarget/SnowballTarget-399928.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64c7a453877b3eb4c12f616844f8e08e5e8226b2bfc1cde00e88151d80b1106f
+size 260484

SnowballTarget/SnowballTarget-399928.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db4e2b3ee72028b313753bf3440a293abf68db625940e292d5208927e9a36d56
+size 1588526

SnowballTarget/SnowballTarget-400120.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64c7a453877b3eb4c12f616844f8e08e5e8226b2bfc1cde00e88151d80b1106f
+size 260484

SnowballTarget/SnowballTarget-400120.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f98be8755f9487cc04d3e5776ab35a95dbbda554b0b451627ec7d219a07d24c6
+size 1588526

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe8ac531dd03c6c9329ff7a6835994a182545cd977e846220e4a347e319ddac0
-size 784804
+oid sha256:f98be8755f9487cc04d3e5776ab35a95dbbda554b0b451627ec7d219a07d24c6
+size 1588526

SnowballTarget/events.out.tfevents.1689921906.4ba227ddcbc5.32434.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0407594d9f949af3fd7d74d80eda5c319b759db85d51ef22c0a2bd492f2dbc5b
+size 51619

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": 0.25, "lambd": 0.95, "num_epoch": 5, "shared_critic": true, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 10000, "network_settings": {"normalize": false, "hidden_units": 128, "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": 96, "summary_freq": 5000, "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": 0.25, "lambd": 0.95, "num_epoch": 5, "shared_critic": true, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 10000, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 0.9, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "curiosity": {"gamma": 0.99, "strength": 0.2, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0005, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 400000, "time_horizon": 96, "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": "SnowballTargetCurious", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -26,7 +26,7 @@ behaviors:
     reward_signals:
       extrinsic:
         gamma: 0.99
-        strength: 1.0
+        strength: 0.9
         network_settings:
           normalize: false
           hidden_units: 128
@@ -35,12 +35,25 @@ behaviors:
           memory: null
           goal_conditioning_type: hyper
           deterministic: false
+      curiosity:
+        gamma: 0.99
+        strength: 0.2
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+        learning_rate: 0.0005
+        encoding_size: null
     init_path: null
     keep_checkpoints: 10
     even_checkpoints: false
-    max_steps: 200000
+    max_steps: 400000
     time_horizon: 96
-    summary_freq: 5000
+    summary_freq: 10000
     threaded: true
     self_play: null
     behavioral_cloning: null
@@ -64,11 +77,11 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: SnowballTarget1
+  run_id: SnowballTargetCurious
   initialize_from: null
   load_model: false
   resume: false
-  force: false
+  force: true
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/training-envs-executables/linux/SnowballTarge
 Mono config path = '/content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/SnowballTarget
-Unable to load player prefs
 Initialize engine version: 2021.3.14f1 (eee1884e7226)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.082 seconds
+- Completed reload, in  0.079 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -45,7 +42,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.673895 ms
+UnloadTime: 0.716327 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]: 5374 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]: 10741 frames, [16.0 KB-32.0 KB]: 182 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
@@ -169,22 +166,22 @@ 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]: 5466 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 10918 frames, [8.0 MB-16.0 MB]: 6 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 6.7 MB
+      Peak Allocated memory 9.3 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 5466 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 10924 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.8 MB
+      Peak Allocated memory 17.3 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 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]: 4365 frames, [64.0 KB-128.0 KB]: 1101 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 10392 frames, [64.0 KB-128.0 KB]: 532 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 67.3 KB
+      Peak Allocated memory 66.4 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 5466 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 10924 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]: 5466 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 10924 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]: 5465 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 10923 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]: 5466 frames
+      Peak usage frame count: [0-1.0 KB]: 10924 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]: 5466 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 10924 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -2,39 +2,51 @@
     "name": "root",
     "gauges": {
         "SnowballTarget.Policy.Entropy.mean": {
-            "value": 0.9074764847755432,
-            "min": 0.8980207443237305,
-            "max": 2.887725353240967,
+            "value": 0.7823862433433533,
+            "min": 0.7754074335098267,
+            "max": 2.87212872505188,
             "count": 40
         },
         "SnowballTarget.Policy.Entropy.sum": {
-            "value": 4102.701171875,
-            "min": 4102.701171875,
-            "max": 16009.548828125,
+            "value": 6962.455078125,
+            "min": 6900.3505859375,
+            "max": 31340.669921875,
             "count": 40
         },
         "SnowballTarget.Step.mean": {
-            "value": 199920.0,
-            "min": 4976.0,
-            "max": 199920.0,
+            "value": 399928.0,
+            "min": 9952.0,
+            "max": 399928.0,
             "count": 40
         },
         "SnowballTarget.Step.sum": {
-            "value": 199920.0,
-            "min": 4976.0,
-            "max": 199920.0,
+            "value": 399928.0,
+            "min": 9952.0,
+            "max": 399928.0,
             "count": 40
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 12.52747631072998,
-            "min": 0.09490196406841278,
-            "max": 12.592220306396484,
+            "value": 12.034942626953125,
+            "min": 0.45372357964515686,
+            "max": 12.034942626953125,
             "count": 40
         },
         "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 901.978271484375,
-            "min": 6.83294153213501,
-            "max": 1038.786865234375,
+            "value": 1733.03173828125,
+            "min": 65.33619689941406,
+            "max": 1863.9541015625,
+            "count": 40
+        },
+        "SnowballTarget.Policy.CuriosityValueEstimate.mean": {
+            "value": 0.705839991569519,
+            "min": 0.15340012311935425,
+            "max": 1.2888423204421997,
+            "count": 40
+        },
+        "SnowballTarget.Policy.CuriosityValueEstimate.sum": {
+            "value": 101.64096069335938,
+            "min": 22.089616775512695,
+            "max": 197.5901641845703,
             "count": 40
         },
         "SnowballTarget.Environment.EpisodeLength.mean": {
@@ -44,93 +56,129 @@
             "count": 40
         },
         "SnowballTarget.Environment.EpisodeLength.sum": {
-            "value": 6567.0,
-            "min": 4378.0,
-            "max": 6567.0,
+            "value": 10945.0,
+            "min": 8756.0,
+            "max": 10945.0,
             "count": 40
         },
         "SnowballTarget.Losses.PolicyLoss.mean": {
-            "value": 0.07068405189210727,
-            "min": 0.06319188880186309,
-            "max": 0.07711656137079818,
+            "value": 0.06742327443161604,
+            "min": 0.0635198512355975,
+            "max": 0.07569230777824379,
             "count": 40
         },
         "SnowballTarget.Losses.PolicyLoss.sum": {
-            "value": 0.14136810378421455,
-            "min": 0.12638377760372618,
-            "max": 0.22135205152216098,
+            "value": 0.26969309772646416,
+            "min": 0.25407940494239,
+            "max": 0.3784615388912189,
             "count": 40
         },
         "SnowballTarget.Losses.ValueLoss.mean": {
-            "value": 0.20135490622590568,
-            "min": 0.10407538581091691,
-            "max": 0.2827119831653202,
+            "value": 0.0851801988285254,
+            "min": 0.05186068983508877,
+            "max": 0.10859993385041461,
             "count": 40
         },
         "SnowballTarget.Losses.ValueLoss.sum": {
-            "value": 0.40270981245181137,
-            "min": 0.20815077162183382,
-            "max": 0.7716041477287517,
+            "value": 0.3407207953141016,
+            "min": 0.20744275934035508,
+            "max": 0.5272768591256702,
             "count": 40
         },
         "SnowballTarget.Policy.LearningRate.mean": {
-            "value": 4.782098406000002e-06,
-            "min": 4.782098406000002e-06,
-            "max": 0.000295182001606,
+            "value": 3.825098724999996e-06,
+            "min": 3.825098724999996e-06,
+            "max": 0.000295941001353,
             "count": 40
         },
         "SnowballTarget.Policy.LearningRate.sum": {
-            "value": 9.564196812000005e-06,
-            "min": 9.564196812000005e-06,
-            "max": 0.0008211960262679999,
+            "value": 1.5300394899999985e-05,
+            "min": 1.5300394899999985e-05,
+            "max": 0.00144225001925,
             "count": 40
         },
         "SnowballTarget.Policy.Epsilon.mean": {
-            "value": 0.10239100000000001,
-            "min": 0.10239100000000001,
-            "max": 0.24759100000000003,
+            "value": 0.10191249999999999,
+            "min": 0.10191249999999999,
+            "max": 0.2479705,
             "count": 40
         },
         "SnowballTarget.Policy.Epsilon.sum": {
-            "value": 0.20478200000000002,
-            "min": 0.20478200000000002,
-            "max": 0.7105980000000001,
+            "value": 0.40764999999999996,
+            "min": 0.40764999999999996,
+            "max": 1.221125,
             "count": 40
         },
         "SnowballTarget.Policy.Beta.mean": {
-            "value": 8.954060000000004e-05,
-            "min": 8.954060000000004e-05,
-            "max": 0.004919860599999999,
+            "value": 7.362249999999992e-05,
+            "min": 7.362249999999992e-05,
+            "max": 0.0049324853,
             "count": 40
         },
         "SnowballTarget.Policy.Beta.sum": {
-            "value": 0.00017908120000000008,
-            "min": 0.00017908120000000008,
-            "max": 0.0136892268,
+            "value": 0.0002944899999999997,
+            "min": 0.0002944899999999997,
+            "max": 0.024039425,
+            "count": 40
+        },
+        "SnowballTarget.Losses.CuriosityForwardLoss.mean": {
+            "value": 0.04188172720810946,
+            "min": 0.033935607860193534,
+            "max": 0.08911535578560742,
+            "count": 40
+        },
+        "SnowballTarget.Losses.CuriosityForwardLoss.sum": {
+            "value": 0.16752690883243784,
+            "min": 0.13837627082624857,
+            "max": 0.3564614231424297,
+            "count": 40
+        },
+        "SnowballTarget.Losses.CuriosityInverseLoss.mean": {
+            "value": 0.6003185132847113,
+            "min": 0.5939198171391207,
+            "max": 2.693057048539905,
+            "count": 40
+        },
+        "SnowballTarget.Losses.CuriosityInverseLoss.sum": {
+            "value": 2.4012740531388452,
+            "min": 2.4012740531388452,
+            "max": 11.969808614955229,
             "count": 40
         },
         "SnowballTarget.Environment.CumulativeReward.mean": {
-            "value": 24.772727272727273,
-            "min": 2.8636363636363638,
-            "max": 25.09090909090909,
+            "value": 25.931818181818183,
+            "min": 3.25,
+            "max": 26.204545454545453,
             "count": 40
         },
         "SnowballTarget.Environment.CumulativeReward.sum": {
-            "value": 545.0,
-            "min": 63.0,
-            "max": 808.0,
+            "value": 1141.0,
+            "min": 143.0,
+            "max": 1441.0,
             "count": 40
         },
         "SnowballTarget.Policy.ExtrinsicReward.mean": {
-            "value": 24.772727272727273,
-            "min": 2.8636363636363638,
-            "max": 25.09090909090909,
+            "value": 23.338635753501546,
+            "min": 2.9249998954209415,
+            "max": 23.584090276197955,
             "count": 40
         },
         "SnowballTarget.Policy.ExtrinsicReward.sum": {
-            "value": 545.0,
-            "min": 63.0,
-            "max": 808.0,
+            "value": 1026.899973154068,
+            "min": 128.69999539852142,
+            "max": 1296.8999617099762,
+            "count": 40
+        },
+        "SnowballTarget.Policy.CuriosityReward.mean": {
+            "value": 1.5325787596997211,
+            "min": 1.4327925314618783,
+            "max": 2.6246763768859886,
+            "count": 40
+        },
+        "SnowballTarget.Policy.CuriosityReward.sum": {
+            "value": 67.43346542678773,
+            "min": 63.73716417513788,
+            "max": 144.35720072872937,
             "count": 40
         },
         "SnowballTarget.IsTraining.mean": {
@@ -148,67 +196,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1689914868",
+        "start_time_seconds": "1689921905",
         "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./ppo_snowballtarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./ppo_snowballtarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTargetCurious --no-graphics --force",
         "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": "1689915421"
+        "end_time_seconds": "1689923075"
     },
-    "total": 552.590371831,
+    "total": 1170.717425587999,
     "count": 1,
-    "self": 0.8758308999999826,
+    "self": 0.42497604499931185,
     "children": {
         "run_training.setup": {
-            "total": 0.03300840200006405,
+            "total": 0.03128317899972899,
             "count": 1,
-            "self": 0.03300840200006405
+            "self": 0.03128317899972899
         },
         "TrainerController.start_learning": {
-            "total": 551.6815325289999,
+            "total": 1170.261166364,
             "count": 1,
-            "self": 0.6336164739990409,
+            "self": 1.0667345250103608,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 6.078368554999997,
+                    "total": 4.5801261289998365,
                     "count": 1,
-                    "self": 6.078368554999997
+                    "self": 4.5801261289998365
                 },
                 "TrainerController.advance": {
-                    "total": 544.7398578980009,
-                    "count": 18218,
-                    "self": 0.30483696400312965,
+                    "total": 1164.4760683689901,
+                    "count": 36412,
+                    "self": 0.5050375901291773,
                     "children": {
                         "env_step": {
-                            "total": 544.4350209339977,
-                            "count": 18218,
-                            "self": 397.6144213920046,
+                            "total": 1163.971030778861,
+                            "count": 36412,
+                            "self": 873.7409455367024,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 146.50968025798602,
-                                    "count": 18218,
-                                    "self": 1.9840145679867192,
+                                    "total": 289.68929279413896,
+                                    "count": 36412,
+                                    "self": 3.2346155361719866,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 144.5256656899993,
-                                            "count": 18218,
-                                            "self": 144.5256656899993
+                                            "total": 286.454677257967,
+                                            "count": 36412,
+                                            "self": 286.454677257967
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.3109192840071273,
-                                    "count": 18218,
+                                    "total": 0.5407924480196016,
+                                    "count": 36412,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 549.7212558960065,
-                                            "count": 18218,
+                                            "total": 1167.2430328119744,
+                                            "count": 36412,
                                             "is_parallel": true,
-                                            "self": 284.3714180130047,
+                                            "self": 681.4198886719532,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +265,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0063523060000534315,
+                                                            "total": 0.0018927660003100755,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.004795859000068958,
+                                                            "self": 0.000562683999305591,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0015564469999844732,
+                                                                    "total": 0.0013300820010044845,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0015564469999844732
+                                                                    "self": 0.0013300820010044845
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.0849465590000591,
+                                                            "total": 0.06856268100000307,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0009313829999655354,
+                                                            "self": 0.0005964209994999692,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004525500000909233,
+                                                                    "total": 0.0003943410001738812,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004525500000909233
+                                                                    "self": 0.0003943410001738812
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.08036101599998347,
+                                                                    "total": 0.06546917000014219,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.08036101599998347
+                                                                    "self": 0.06546917000014219
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0032016100000191727,
+                                                                    "total": 0.002102749000187032,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0007062609996637548,
+                                                                    "self": 0.0005411560005086358,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.002495349000355418,
+                                                                            "total": 0.0015615929996783962,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.002495349000355418
+                                                                            "self": 0.0015615929996783962
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +315,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 265.3498378830018,
-                                                    "count": 18217,
+                                                    "total": 485.8231441400212,
+                                                    "count": 36411,
                                                     "is_parallel": true,
-                                                    "self": 11.18796804900171,
+                                                    "self": 20.639413553023587,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 5.470085376996963,
-                                                            "count": 18217,
+                                                            "total": 10.078052166051748,
+                                                            "count": 36411,
                                                             "is_parallel": true,
-                                                            "self": 5.470085376996963
+                                                            "self": 10.078052166051748
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 212.13326891400357,
-                                                            "count": 18217,
+                                                            "total": 387.16746825984774,
+                                                            "count": 36411,
                                                             "is_parallel": true,
-                                                            "self": 212.13326891400357
+                                                            "self": 387.16746825984774
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 36.558515542999544,
-                                                            "count": 18217,
+                                                            "total": 67.93821016109814,
+                                                            "count": 36411,
                                                             "is_parallel": true,
-                                                            "self": 7.096372885992309,
+                                                            "self": 12.569071423020432,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 29.462142657007234,
-                                                                    "count": 182170,
+                                                                    "total": 55.36913873807771,
+                                                                    "count": 364110,
                                                                     "is_parallel": true,
-                                                                    "self": 29.462142657007234
+                                                                    "self": 55.36913873807771
                                                                 }
                                                             }
                                                         }
@@ -309,9 +357,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 0.00027281200004836137,
+                    "total": 0.00020994999977119733,
                     "count": 1,
-                    "self": 0.00027281200004836137,
+                    "self": 0.00020994999977119733,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -320,36 +368,36 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 541.8961593720343,
-                                    "count": 354203,
+                                    "total": 1165.3188830539748,
+                                    "count": 22648,
                                     "is_parallel": true,
-                                    "self": 7.870481475088809,
+                                    "self": 0.5316522920466014,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 215.14901628794598,
-                                            "count": 354203,
+                                            "total": 165.31442269693162,
+                                            "count": 22648,
                                             "is_parallel": true,
-                                            "self": 210.52944220694633,
+                                            "self": 155.09521240393315,
                                             "children": {
                                                 "RLTrainer._checkpoint": {
-                                                    "total": 4.619574080999655,
-                                                    "count": 20,
+                                                    "total": 10.219210292998469,
+                                                    "count": 40,
                                                     "is_parallel": true,
-                                                    "self": 4.619574080999655
+                                                    "self": 10.219210292998469
                                                 }
                                             }
                                         },
                                         "_update_policy": {
-                                            "total": 318.8766616089995,
-                                            "count": 90,
+                                            "total": 999.4728080649966,
+                                            "count": 181,
                                             "is_parallel": true,
-                                            "self": 125.46813759000077,
+                                            "self": 622.892439668005,
                                             "children": {
                                                 "TorchPPOOptimizer.update": {
-                                                    "total": 193.40852401899872,
-                                                    "count": 7645,
+                                                    "total": 376.5803683969916,
+                                                    "count": 15380,
                                                     "is_parallel": true,
-                                                    "self": 193.40852401899872
+                                                    "self": 376.5803683969916
                                                 }
                                             }
                                         }
@@ -360,14 +408,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.2294167899999593,
+                    "total": 0.13802739099992323,
                     "count": 1,
-                    "self": 0.0010001840000768425,
+                    "self": 0.0007361719999607885,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.22841660599988245,
+                            "total": 0.13729121899996244,
                             "count": 1,
-                            "self": 0.22841660599988245
+                            "self": 0.13729121899996244
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,103 +2,103 @@
     "SnowballTarget": {
         "checkpoints": [
             {
-                "steps": 119952,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-119952.onnx",
-                "reward": 21.454545454545453,
-                "creation_time": 1689915197.0312555,
+                "steps": 319960,
+                "file_path": "results/SnowballTargetCurious/SnowballTarget/SnowballTarget-319960.onnx",
+                "reward": null,
+                "creation_time": 1689922845.003947,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-119952.pt"
+                    "results/SnowballTargetCurious/SnowballTarget/SnowballTarget-319960.pt"
                 ]
             },
             {
-                "steps": 129992,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-129992.onnx",
-                "reward": 22.636363636363637,
-                "creation_time": 1689915226.046242,
+                "steps": 329992,
+                "file_path": "results/SnowballTargetCurious/SnowballTarget/SnowballTarget-329992.onnx",
+                "reward": 26.3,
+                "creation_time": 1689922871.4831252,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-129992.pt"
+                    "results/SnowballTargetCurious/SnowballTarget/SnowballTarget-329992.pt"
                 ]
             },
             {
-                "steps": 139944,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-139944.onnx",
-                "reward": 24.90909090909091,
-                "creation_time": 1689915251.506197,
+                "steps": 339952,
+                "file_path": "results/SnowballTargetCurious/SnowballTarget/SnowballTarget-339952.onnx",
+                "reward": null,
+                "creation_time": 1689922902.8197052,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-139944.pt"
+                    "results/SnowballTargetCurious/SnowballTarget/SnowballTarget-339952.pt"
                 ]
             },
             {
-                "steps": 149984,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.onnx",
-                "reward": 23.818181818181817,
-                "creation_time": 1689915279.6826274,
+                "steps": 349992,
+                "file_path": "results/SnowballTargetCurious/SnowballTarget/SnowballTarget-349992.onnx",
+                "reward": null,
+                "creation_time": 1689922934.255856,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-149984.pt"
+                    "results/SnowballTargetCurious/SnowballTarget/SnowballTarget-349992.pt"
                 ]
             },
             {
-                "steps": 159936,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-159936.onnx",
-                "reward": 24.0,
-                "creation_time": 1689915305.8110385,
+                "steps": 359944,
+                "file_path": "results/SnowballTargetCurious/SnowballTarget/SnowballTarget-359944.onnx",
+                "reward": null,
+                "creation_time": 1689922960.0544336,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-159936.pt"
+                    "results/SnowballTargetCurious/SnowballTarget/SnowballTarget-359944.pt"
                 ]
             },
             {
-                "steps": 169976,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-169976.onnx",
-                "reward": 24.181818181818183,
-                "creation_time": 1689915334.796858,
+                "steps": 369984,
+                "file_path": "results/SnowballTargetCurious/SnowballTarget/SnowballTarget-369984.onnx",
+                "reward": null,
+                "creation_time": 1689922991.6703765,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-169976.pt"
+                    "results/SnowballTargetCurious/SnowballTarget/SnowballTarget-369984.pt"
                 ]
             },
             {
-                "steps": 179928,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-179928.onnx",
-                "reward": 25.454545454545453,
-                "creation_time": 1689915363.8239555,
+                "steps": 379936,
+                "file_path": "results/SnowballTargetCurious/SnowballTarget/SnowballTarget-379936.onnx",
+                "reward": null,
+                "creation_time": 1689923017.6110141,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-179928.pt"
+                    "results/SnowballTargetCurious/SnowballTarget/SnowballTarget-379936.pt"
                 ]
             },
             {
-                "steps": 189968,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-189968.onnx",
-                "reward": 24.0,
-                "creation_time": 1689915393.1039462,
+                "steps": 389976,
+                "file_path": "results/SnowballTargetCurious/SnowballTarget/SnowballTarget-389976.onnx",
+                "reward": null,
+                "creation_time": 1689923048.6691453,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-189968.pt"
+                    "results/SnowballTargetCurious/SnowballTarget/SnowballTarget-389976.pt"
                 ]
             },
             {
-                "steps": 199920,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-199920.onnx",
-                "reward": 23.90909090909091,
-                "creation_time": 1689915420.3405128,
+                "steps": 399928,
+                "file_path": "results/SnowballTargetCurious/SnowballTarget/SnowballTarget-399928.onnx",
+                "reward": null,
+                "creation_time": 1689923075.3943675,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-199920.pt"
+                    "results/SnowballTargetCurious/SnowballTarget/SnowballTarget-399928.pt"
                 ]
             },
             {
-                "steps": 200112,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.onnx",
-                "reward": 23.90909090909091,
-                "creation_time": 1689915420.6127658,
+                "steps": 400120,
+                "file_path": "results/SnowballTargetCurious/SnowballTarget/SnowballTarget-400120.onnx",
+                "reward": null,
+                "creation_time": 1689923075.5676386,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                    "results/SnowballTargetCurious/SnowballTarget/SnowballTarget-400120.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 200112,
-            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": 23.90909090909091,
-            "creation_time": 1689915420.6127658,
+            "steps": 400120,
+            "file_path": "results/SnowballTargetCurious/SnowballTarget.onnx",
+            "reward": null,
+            "creation_time": 1689923075.5676386,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-200112.pt"
+                "results/SnowballTargetCurious/SnowballTarget/SnowballTarget-400120.pt"
             ]
         }
     },