first push

README.md

@@ -0,0 +1,35 @@
+---
+library_name: ml-agents
+tags:
+- Worm
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-Worm
+---
+
+  # **ppo** Agent playing **Worm**
+  This is a trained model of a **ppo** agent playing **Worm**
+  using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
+
+  ## Usage (with ML-Agents)
+  The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
+
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+  - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
+  browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
+  - A *longer tutorial* to understand how works ML-Agents:
+  https://huggingface.co/learn/deep-rl-course/unit5/introduction
+
+  ### Resume the training
+  ```bash
+  mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
+  ```
+
+  ### Watch your Agent play
+  You can watch your agent **playing directly in your browser**
+
+  1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
+  2. Step 1: Find your model_id: mjishu/worm1
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

Worm.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c335f79ae4366f767457cf2d53253e8fa508a62fd2aeaa0811b82fa17a88c864
+size 2259626

Worm/Worm-2499000.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b73e329b62143674c4a3f49bafcd98683dad2cf481cde8ccfb710e76c9b0ee69
+size 2259626

Worm/Worm-2499000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a4c9d48d71ca0bb9d372d459e69c0aa030b5fd8a1ce24c328f0dc2014e4e844
+size 13496972

Worm/Worm-2999000.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b041ddda58216e12a1517c5762bf52c1da64e6337c2f7f7973963e6f8a898da
+size 2259626

Worm/Worm-2999000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aa58d71a59e1a183ee2ba51988b355398ca510082e42fd58f22ac199ae1a997
+size 13496972

Worm/Worm-3499000.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d0716055a9f876c9754bc5af82d00b4881e1979e1fd20feb740b586c3f5fef6
+size 2259626

Worm/Worm-3499000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03c0ae5ed40edb6e597facde3aed5e5f0089a7ab0c09e97f27012351447c5583
+size 13496972

Worm/Worm-3999000.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f18f6afc84777761520d9a3020b154464a4392911357a145db4195f348a608d4
+size 2259626

Worm/Worm-3999000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f16616c4b755cb6ab7695d68518cb813698973fbc38567dc1662fe6c833aea26
+size 13496972

Worm/Worm-4010000.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c335f79ae4366f767457cf2d53253e8fa508a62fd2aeaa0811b82fa17a88c864
+size 2259626

Worm/Worm-4010000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22267e76dc8386a6bfea45915ed96cc5277ec906665533834f8187be13df29c9
+size 13496972

Worm/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54e038d738545f01dd872253fefff9929f03ea6936e812a5213c920ab3510592
+size 13496802

Worm/events.out.tfevents.1739384861.computerj.1046301.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63d77a8163ef0a668a3951bb6a65e60d1be2b59e214e3579c64f03916c0a30e7
+size 186164

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"Worm": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2024, "buffer_size": 20240, "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": 500000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "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": 5, "even_checkpoints": false, "max_steps": 4000000, "time_horizon": 1000, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "../training-envs-executables/linux/Worm/Worm", "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": false, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Worm1", "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

@@ -0,0 +1,79 @@
+default_settings: null
+behaviors:
+  Worm:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 2024
+      buffer_size: 20240
+      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: 500000
+    network_settings:
+      normalize: true
+      hidden_units: 512
+      num_layers: 3
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.995
+        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: 5
+    even_checkpoints: false
+    max_steps: 4000000
+    time_horizon: 1000
+    summary_freq: 30000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ../training-envs-executables/linux/Worm/Worm
+  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: false
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: Worm1
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: true
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,335 @@
+Mono path[0] = '/root/coding/ML/reinforcment-learning/unit5/training-envs-executables/linux/Worm/Worm_Data/Managed'
+Mono config path = '/root/coding/ML/reinforcment-learning/unit5/training-envs-executables/linux/Worm/Worm_Data/MonoBleedingEdge/etc'
+Found 4 interfaces on host : 0) 10.255.255.254 1) 172.25.35.194 2) 172.18.0.1 3) 172.17.0.1
+Multi-casting "[IP] 10.255.255.254 [Port] 55499 [Flags] 2 [Guid] 1698677593 [EditorId] 588871222 [Version] 1048832 [Id] LinuxPlayer(13,172.25.35.194) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+Display 0 'XWAYLAND0': 3440x1440 (primary device).
+PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
+PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
+Unable to load player prefs
+Desktop is 3440 x 1440 @ 60 Hz
+Invalid initial resolution 80 x 80 - forcing to 100 x 100
+Initialize engine version: 2021.3.5f1 (40eb3a945986)
+[Subsystems] Discovering subsystems at path /root/coding/ML/reinforcment-learning/unit5/training-envs-executables/linux/Worm/Worm_Data/UnitySubsystems
+GfxDevice: creating device client; threaded=1; jobified=0
+Renderer: D3D12 (AMD Radeon(TM) Graphics)
+Vendor:   Microsoft Corporation
+Version:  4.2 (Core Profile) Mesa 23.2.1-1ubuntu3.1~22.04.2
+GLES:     0
+ GL_AMD_conservative_depth GL_AMD_draw_buffers_blend GL_AMD_gpu_shader_int64 GL_AMD_multi_draw_indirect GL_AMD_shader_stencil_export GL_AMD_shader_trinary_minmax GL_AMD_texture_texture4 GL_AMD_vertex_shader_layer GL_AMD_vertex_shader_viewport_index GL_ANGLE_texture_compression_dxt3 GL_ANGLE_texture_compression_dxt5 GL_ARB_ES2_compatibility GL_ARB_ES3_1_compatibility GL_ARB_ES3_compatibility GL_ARB_arrays_of_arrays GL_ARB_base_instance GL_ARB_blend_func_extended GL_ARB_buffer_storage GL_ARB_clear_buffer_object GL_ARB_clear_texture GL_ARB_clip_control GL_ARB_compressed_texture_pixel_storage GL_ARB_compute_shader GL_ARB_compute_variable_group_size GL_ARB_conditional_render_inverted GL_ARB_conservative_depth GL_ARB_copy_buffer GL_ARB_debug_output GL_ARB_depth_buffer_float GL_ARB_depth_clamp GL_ARB_direct_state_access GL_ARB_draw_buffers GL_ARB_draw_buffers_blend GL_ARB_draw_elements_base_vertex GL_ARB_draw_indirect GL_ARB_draw_instanced GL_ARB_explicit_attrib_location GL_ARB_explicit_uniform_location GL_ARB_frag
+ment_coord_conventions GL_ARB_fragment_layer_viewport GL_ARB_fragment_shader GL_ARB_framebuffer_no_attachments GL_ARB_framebuffer_object GL_ARB_framebuffer_sRGB GL_ARB_get_program_binary GL_ARB_get_texture_sub_image GL_ARB_gpu_shader5 GL_ARB_gpu_shader_fp64 GL_ARB_gpu_shader_int64 GL_ARB_half_float_pixel GL_ARB_half_float_vertex GL_ARB_indirect_parameters GL_ARB_instanced_arrays GL_ARB_internalformat_query GL_ARB_internalformat_query2 GL_ARB_invalidate_subdata GL_ARB_map_buffer_alignment GL_ARB_map_buffer_range GL_ARB_multi_bind GL_ARB_multi_draw_indirect GL_ARB_occlusion_query2 GL_ARB_parallel_shader_compile GL_ARB_pixel_buffer_object GL_ARB_point_sprite GL_ARB_program_interface_query GL_ARB_provoking_vertex GL_ARB_robust_buffer_access_behavior GL_ARB_robustness GL_ARB_sample_shading GL_ARB_sampler_objects GL_ARB_seamless_cube_map GL_ARB_separate_shader_objects GL_ARB_shader_atomic_counter_ops GL_ARB_shader_atomic_counters GL_ARB_shader_bit_encoding GL_ARB_shader_draw_parameters GL_ARB_shader_image_load_sto
+re GL_ARB_shader_image_size GL_ARB_shader_objects GL_ARB_shader_precision GL_ARB_shader_stencil_export GL_ARB_shader_storage_buffer_object GL_ARB_shader_subroutine GL_ARB_shader_texture_lod GL_ARB_shading_language_420pack GL_ARB_shading_language_include GL_ARB_shading_language_packing GL_ARB_stencil_texturing GL_ARB_sync GL_ARB_tessellation_shader GL_ARB_texture_buffer_object GL_ARB_texture_buffer_object_rgb32 GL_ARB_texture_buffer_range GL_ARB_texture_compression_bptc GL_ARB_texture_compression_rgtc GL_ARB_texture_cube_map_array GL_ARB_texture_filter_anisotropic GL_ARB_texture_float GL_ARB_texture_gather GL_ARB_texture_multisample GL_ARB_texture_non_power_of_two GL_ARB_texture_query_levels GL_ARB_texture_query_lod GL_ARB_texture_rectangle GL_ARB_texture_rg GL_ARB_texture_rgb10_a2ui GL_ARB_texture_stencil8 GL_ARB_texture_storage GL_ARB_texture_storage_multisample GL_ARB_texture_swizzle GL_ARB_timer_query GL_ARB_transform_feedback2 GL_ARB_transform_feedback3 GL_ARB_transform_feedback_instanced GL_ARB_uniform_
+buffer_object GL_ARB_vertex_array_bgra GL_ARB_vertex_array_object GL_ARB_vertex_attrib_64bit GL_ARB_vertex_attrib_binding GL_ARB_vertex_buffer_object GL_ARB_vertex_shader GL_ARB_vertex_type_10f_11f_11f_rev GL_ARB_vertex_type_2_10_10_10_rev GL_ARB_viewport_array GL_ATI_blend_equation_separate GL_ATI_texture_float GL_EXT_EGL_image_storage GL_EXT_EGL_sync GL_EXT_abgr GL_EXT_blend_equation_separate GL_EXT_debug_label GL_EXT_draw_buffers2 GL_EXT_draw_instanced GL_EXT_framebuffer_blit GL_EXT_framebuffer_multisample GL_EXT_framebuffer_multisample_blit_scaled GL_EXT_framebuffer_object GL_EXT_framebuffer_sRGB GL_EXT_memory_object GL_EXT_memory_object_fd GL_EXT_packed_depth_stencil GL_EXT_packed_float GL_EXT_pixel_buffer_object GL_EXT_provoking_vertex GL_EXT_semaphore GL_EXT_semaphore_fd GL_EXT_shader_integer_mix GL_EXT_texture_array GL_EXT_texture_compression_dxt1 GL_EXT_texture_compression_rgtc GL_EXT_texture_compression_s3tc GL_EXT_texture_filter_anisotropic GL_EXT_texture_integer GL_EXT_texture_sRGB GL_EXT_texture
+_sRGB_decode GL_EXT_texture_shared_exponent GL_EXT_texture_snorm GL_EXT_texture_swizzle GL_EXT_timer_query GL_EXT_transform_feedback GL_EXT_vertex_array_bgra GL_EXT_vertex_attrib_64bit GL_IBM_multimode_draw_arrays GL_KHR_context_flush_control GL_KHR_debug GL_KHR_no_error GL_KHR_parallel_shader_compile GL_KHR_robust_buffer_access_behavior GL_KHR_robustness GL_KHR_texture_compression_astc_ldr GL_KHR_texture_compression_astc_sliced_3d GL_MESA_pack_invert GL_MESA_shader_integer_functions GL_MESA_texture_signed_rgba GL_NV_conditional_render GL_NV_copy_image GL_NV_depth_clamp GL_NV_packed_depth_stencil GL_NV_vdpau_interop GL_OES_EGL_image GL_S3_s3tc
+OPENGL LOG: Creating OpenGL 4.2 graphics device ; Context level  <OpenGL 4.2> ; Context handle 884833552
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.053 seconds
+Default vsync count 1
+requesting resize 80 x 80
+resizing window to 80 x 80
+Desktop is 3440 x 1440 @ 60 Hz
+Desktop is 3440 x 1440 @ 60 Hz
+UnloadTime: 0.606970 ms
+Setting up 6 worker threads for Enlighten.
+requesting resize 84 x 84
+resizing window to 84 x 84
+Desktop is 3440 x 1440 @ 60 Hz
+PlayerConnection::CleanupMemory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [4.0 KB-8.0 KB]: 80179 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AUDIO_FMOD stream thread]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 8]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 10]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 1.2 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 284.0 KB
+      Peak Allocated Bytes 243.3 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AUDIO_FMOD PulseAudio Mixer]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Profiler.Dispatcher]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 1.9 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 11
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 1.2 KB
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 6
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_UnityGfxDeviceWorker]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 45.0 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 9]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 1.2 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 1.2 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 128 B
+      Overflow Count 0
+[ALLOC_MEMORYPROFILER]
+  Peak usage frame count: [64.0 KB-128.0 KB]: 80180 frames
+  Requested Block Size 1.0 MB
+  Peak Block count 1
+  Peak Allocated memory 119.7 KB
+  Peak Large allocation bytes 0 B
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 30
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.2 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [8.0 MB-16.0 MB]: 80180 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 13.8 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 80180 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.9 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 1
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.2 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [64.0 KB-128.0 KB]: 80179 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.7 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [64.0 KB-128.0 KB]: 80179 frames, [128.0 KB-256.0 KB]: 1 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 151.7 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.2 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [1.0 MB-2.0 MB]: 80180 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.2 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_CACHEOBJECTS_THREAD]
+      Peak usage frame count: [2.0 MB-4.0 MB]: 80179 frames, [8.0 MB-16.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 3
+      Peak Allocated memory 8.1 MB
+      Peak Large allocation bytes 0 B
+[ALLOC_TYPETREE] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.2 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 80180 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: [4.0 KB-8.0 KB]: 80179 frames, [8.0 KB-16.0 KB]: 1 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 9.3 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_PROFILER]
+  Peak usage frame count: [32.0 KB-64.0 KB]: 80180 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 40.0 KB
+  Peak Large allocation bytes 0 B
+    [ALLOC_PROFILER_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 300 B
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1739389937401,"processId":1046344,"allocatedMemory":2107921,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":141362},{"Thread":34868},{"Manager":16271},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":67733},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":672},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3498},{"DynamicArray":30872},{"HashMap":7680},{"Utility":5440},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -0,0 +1,362 @@
+{
+    "name": "root",
+    "gauges": {
+        "Worm.Policy.Entropy.mean": {
+            "value": 1.0663478374481201,
+            "min": 1.0663478374481201,
+            "max": 1.418938398361206,
+            "count": 133
+        },
+        "Worm.Policy.Entropy.sum": {
+            "value": 31990.43359375,
+            "min": 31990.43359375,
+            "max": 42568.15234375,
+            "count": 133
+        },
+        "Worm.Environment.EpisodeLength.mean": {
+            "value": 999.0,
+            "min": 999.0,
+            "max": 999.0,
+            "count": 133
+        },
+        "Worm.Environment.EpisodeLength.sum": {
+            "value": 29970.0,
+            "min": 29970.0,
+            "max": 29970.0,
+            "count": 133
+        },
+        "Worm.Step.mean": {
+            "value": 3989000.0,
+            "min": 29000.0,
+            "max": 3989000.0,
+            "count": 133
+        },
+        "Worm.Step.sum": {
+            "value": 3989000.0,
+            "min": 29000.0,
+            "max": 3989000.0,
+            "count": 133
+        },
+        "Worm.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 152.24058532714844,
+            "min": -0.013336945325136185,
+            "max": 152.24058532714844,
+            "count": 133
+        },
+        "Worm.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 4567.2177734375,
+            "min": -0.38677141070365906,
+            "max": 4567.2177734375,
+            "count": 133
+        },
+        "Worm.Environment.CumulativeReward.mean": {
+            "value": 782.232725016276,
+            "min": 0.28914098516106607,
+            "max": 782.5456156412761,
+            "count": 133
+        },
+        "Worm.Environment.CumulativeReward.sum": {
+            "value": 23466.98175048828,
+            "min": 8.674229554831982,
+            "max": 23476.36846923828,
+            "count": 133
+        },
+        "Worm.Policy.ExtrinsicReward.mean": {
+            "value": 782.232725016276,
+            "min": 0.28914098516106607,
+            "max": 782.5456156412761,
+            "count": 133
+        },
+        "Worm.Policy.ExtrinsicReward.sum": {
+            "value": 23466.98175048828,
+            "min": 8.674229554831982,
+            "max": 23476.36846923828,
+            "count": 133
+        },
+        "Worm.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 133
+        },
+        "Worm.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 133
+        },
+        "Worm.Losses.PolicyLoss.mean": {
+            "value": 0.015966338155392026,
+            "min": 0.013125823902165783,
+            "max": 0.022229330883073134,
+            "count": 132
+        },
+        "Worm.Losses.PolicyLoss.sum": {
+            "value": 0.015966338155392026,
+            "min": 0.013125823902165783,
+            "max": 0.022229330883073134,
+            "count": 132
+        },
+        "Worm.Losses.ValueLoss.mean": {
+            "value": 9.144103129704794,
+            "min": 0.0015650599601767247,
+            "max": 9.262617429097494,
+            "count": 132
+        },
+        "Worm.Losses.ValueLoss.sum": {
+            "value": 9.144103129704794,
+            "min": 0.0015650599601767247,
+            "max": 9.262617429097494,
+            "count": 132
+        },
+        "Worm.Policy.LearningRate.mean": {
+            "value": 3.0000990000000026e-06,
+            "min": 3.0000990000000026e-06,
+            "max": 0.00029775000075,
+            "count": 132
+        },
+        "Worm.Policy.LearningRate.sum": {
+            "value": 3.0000990000000026e-06,
+            "min": 3.0000990000000026e-06,
+            "max": 0.00029775000075,
+            "count": 132
+        },
+        "Worm.Policy.Epsilon.mean": {
+            "value": 0.101,
+            "min": 0.101,
+            "max": 0.19924999999999998,
+            "count": 132
+        },
+        "Worm.Policy.Epsilon.sum": {
+            "value": 0.101,
+            "min": 0.101,
+            "max": 0.19924999999999998,
+            "count": 132
+        },
+        "Worm.Policy.Beta.mean": {
+            "value": 5.990000000000004e-05,
+            "min": 5.990000000000004e-05,
+            "max": 0.004962575,
+            "count": 132
+        },
+        "Worm.Policy.Beta.sum": {
+            "value": 5.990000000000004e-05,
+            "min": 5.990000000000004e-05,
+            "max": 0.004962575,
+            "count": 132
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1739384855",
+        "python_version": "3.10.12 (main, Jan 17 2025, 14:35:34) [GCC 11.4.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Worm.yaml --env=../training-envs-executables/linux/Worm/Worm --run-id=Worm1 --force",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.5.1+cu124",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1739389937"
+    },
+    "total": 5081.980067805009,
+    "count": 1,
+    "self": 0.3684676999982912,
+    "children": {
+        "run_training.setup": {
+            "total": 0.01631790300598368,
+            "count": 1,
+            "self": 0.01631790300598368
+        },
+        "TrainerController.start_learning": {
+            "total": 5081.5952822020045,
+            "count": 1,
+            "self": 6.492803135333816,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 7.49838720500702,
+                    "count": 1,
+                    "self": 7.49838720500702
+                },
+                "TrainerController.advance": {
+                    "total": 5067.500726156664,
+                    "count": 401000,
+                    "self": 5.571857859467855,
+                    "children": {
+                        "env_step": {
+                            "total": 4551.262668966287,
+                            "count": 401000,
+                            "self": 3480.4544615204213,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 1066.1893351739272,
+                                    "count": 401000,
+                                    "self": 21.103722016123356,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 1045.085613157804,
+                                            "count": 401000,
+                                            "self": 1045.085613157804
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 4.618872271938017,
+                                    "count": 401000,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 5066.994436412206,
+                                            "count": 401000,
+                                            "is_parallel": true,
+                                            "self": 1914.0149631741806,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0006424080056603998,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00015990299289114773,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.00048250501276925206,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00048250501276925206
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.01703754998743534,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00010400600149296224,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0001749119837768376,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0001749119837768376
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.01635050799814053,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.01635050799814053
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.00040812400402501225,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00017267698422074318,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.00023544701980426908,
+                                                                            "count": 2,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.00023544701980426908
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 3152.979473238025,
+                                                    "count": 400999,
+                                                    "is_parallel": true,
+                                                    "self": 33.303838305408135,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 42.738952677027555,
+                                                            "count": 400999,
+                                                            "is_parallel": true,
+                                                            "self": 42.738952677027555
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 2997.1447735649417,
+                                                            "count": 400999,
+                                                            "is_parallel": true,
+                                                            "self": 2997.1447735649417
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 79.79190869064769,
+                                                            "count": 400999,
+                                                            "is_parallel": true,
+                                                            "self": 22.407319652469596,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 57.38458903817809,
+                                                                    "count": 801998,
+                                                                    "is_parallel": true,
+                                                                    "self": 57.38458903817809
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 510.6661993309099,
+                            "count": 401000,
+                            "self": 10.029546890757047,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 129.0715786649671,
+                                    "count": 401000,
+                                    "self": 128.3616090149735,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.7099696499935817,
+                                            "count": 8,
+                                            "self": 0.7099696499935817
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 371.56507377518574,
+                                    "count": 133,
+                                    "self": 227.08188193867682,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 144.48319183650892,
+                                            "count": 5586,
+                                            "self": 144.48319183650892
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 5.00993337482214e-07,
+                    "count": 1,
+                    "self": 5.00993337482214e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.10336520400596783,
+                    "count": 1,
+                    "self": 0.0030298640194814652,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.10033533998648636,
+                            "count": 1,
+                            "self": 0.10033533998648636
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,65 @@
+{
+    "Worm": {
+        "checkpoints": [
+            {
+                "steps": 2499000,
+                "file_path": "results/Worm1/Worm/Worm-2499000.onnx",
+                "reward": 603.0081380208334,
+                "creation_time": 1739388019.7814307,
+                "auxillary_file_paths": [
+                    "results/Worm1/Worm/Worm-2499000.pt"
+                ]
+            },
+            {
+                "steps": 2999000,
+                "file_path": "results/Worm1/Worm/Worm-2999000.onnx",
+                "reward": 666.2186384529903,
+                "creation_time": 1739388653.4007475,
+                "auxillary_file_paths": [
+                    "results/Worm1/Worm/Worm-2999000.pt"
+                ]
+            },
+            {
+                "steps": 3499000,
+                "file_path": "results/Worm1/Worm/Worm-3499000.onnx",
+                "reward": 725.4553929379111,
+                "creation_time": 1739389292.3794954,
+                "auxillary_file_paths": [
+                    "results/Worm1/Worm/Worm-3499000.pt"
+                ]
+            },
+            {
+                "steps": 3999000,
+                "file_path": "results/Worm1/Worm/Worm-3999000.onnx",
+                "reward": 757.3215942382812,
+                "creation_time": 1739389925.4225116,
+                "auxillary_file_paths": [
+                    "results/Worm1/Worm/Worm-3999000.pt"
+                ]
+            },
+            {
+                "steps": 4010000,
+                "file_path": "results/Worm1/Worm/Worm-4010000.onnx",
+                "reward": 766.9546691894532,
+                "creation_time": 1739389937.1817052,
+                "auxillary_file_paths": [
+                    "results/Worm1/Worm/Worm-4010000.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 4010000,
+            "file_path": "results/Worm1/Worm.onnx",
+            "reward": 766.9546691894532,
+            "creation_time": 1739389937.1817052,
+            "auxillary_file_paths": [
+                "results/Worm1/Worm/Worm-4010000.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.5.1+cu124"
+    }
+}