First Push

README.md

@@ -0,0 +1,35 @@
+---
+library_name: ml-agents
+tags:
+- SnowballTarget
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-SnowballTarget
+---
+
+  # **ppo** Agent playing **SnowballTarget**
+  This is a trained model of a **ppo** agent playing **SnowballTarget**
+  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: VicBeltran/ppo-SnowballTarget
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

SnowballTarget.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63df09dee158dfee3e0f063273a6b185f8e4cfe1b56d769fe07fd521d3696c17
+size 646532

SnowballTarget/SnowballTarget-14992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a684d79b11e102d2ff0d6e9df05b3d60a46925beee8bb6b2a4b06f8f9329da50
+size 646532

SnowballTarget/SnowballTarget-14992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7ae0d0e747101d255b20e226007000e51905da555309abca750cb51f147c1a0
+size 3843968

SnowballTarget/SnowballTarget-19992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63df09dee158dfee3e0f063273a6b185f8e4cfe1b56d769fe07fd521d3696c17
+size 646532

SnowballTarget/SnowballTarget-19992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3f3b0317294c30974fe3448630a828653751c9b698000fb73214a625bc3ae66
+size 3843968

SnowballTarget/SnowballTarget-20376.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63df09dee158dfee3e0f063273a6b185f8e4cfe1b56d769fe07fd521d3696c17
+size 646532

SnowballTarget/SnowballTarget-20376.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f11a486294ea63ec8a5aabf12e6ba27b0eeab4fba9ef98f865b921b061f83ff8
+size 3843968

SnowballTarget/SnowballTarget-9952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f10dc1df454264d5793467f60009335a488935cc4c3416b715f5024720e6e47
+size 646532

SnowballTarget/SnowballTarget-9952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d09fd7ea7c2c99b93e29eed17d0e50b81f71118b40c359cfcdc0a018e3ac87b
+size 3843968

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f11a486294ea63ec8a5aabf12e6ba27b0eeab4fba9ef98f865b921b061f83ff8
+size 3843968

SnowballTarget/events.out.tfevents.1692016970.DESKTOP-9GKAG7F.905.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a93826d0b627bd9784cad0ea4f29ca13b99d9eddde487ba4a7308468d05518fb
+size 8019

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 5000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 4, "even_checkpoints": false, "max_steps": 20000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": false}, "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}

configuration.yaml

@@ -0,0 +1,77 @@
+default_settings: null
+behaviors:
+  SnowballTarget:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 5000
+    network_settings:
+      normalize: false
+      hidden_units: 256
+      num_layers: 2
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+    init_path: null
+    keep_checkpoints: 4
+    even_checkpoints: false
+    max_steps: 20000
+    time_horizon: 64
+    summary_freq: 10000
+    threaded: true
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: false
+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

run_logs/Player-0.log

@@ -0,0 +1,282 @@
+Mono path[0] = '/home/victor/pythonprojects/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/home/victor/pythonprojects/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+Display 0 'XWAYLAND0': 2560x1080 (primary device).
+Display 1 'XWAYLAND1 27"': 1920x1080 (secondary device).
+PlayerPrefs - Creating folder: /home/victor/.config/unity3d/Hugging Face
+PlayerPrefs - Creating folder: /home/victor/.config/unity3d/Hugging Face/SnowballTarget
+Unable to load player prefs
+Desktop is 2560 x 1080 @ 60 Hz
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /home/victor/pythonprojects/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
+GfxDevice: creating device client; threaded=1; jobified=1
+Renderer: D3D12 (NVIDIA GeForce RTX 2060)
+Vendor:   Microsoft Corporation
+Version:  4.2 (Core Profile) Mesa 23.0.4-0ubuntu1~22.04.1
+GLES:     0
+ GL_AMD_conservative_depth GL_AMD_draw_buffers_blend GL_AMD_gpu_shader_int64 GL_AMD_multi_draw_indirect GL_AMD_shader_trinary_minmax GL_AMD_texture_texture4 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_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_fragment_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_store GL_ARB_shader_image_size GL_ARB_shader_objects GL_ARB_shader_precision 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_ve
+rtex_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 35055248
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.061 seconds
+Default vsync count 1
+requesting resize 2560 x 1080
+Using native desktop resolution 2560 x 1080
+requesting fullscreen 2560 x 1080 at 0 Hz
+Desktop is 2560 x 1080 @ 60 Hz
+Desktop is 2560 x 1080 @ 60 Hz
+UnloadTime: 1.202800 ms
+requesting resize 84 x 84
+resizing window to 84 x 84
+Desktop is 2560 x 1080 @ 60 Hz
+Setting up 4 worker threads for Enlighten.
+Memory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [8.0 KB-16.0 KB]: 554 frames, [16.0 KB-32.0 KB]: 9 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_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 236 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 304.0 KB
+      Peak Allocated Bytes 228.9 KB
+      Overflow Count 4
+    [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_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 20.3 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 12.1 KB
+      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_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 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 12.1 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_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_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 12.1 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 12.1 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_EnlightenWorker] x 4
+      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 15]
+      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 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_UnityGfxDeviceWorker]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 45.6 KB
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 7
+      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 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 12.1 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 12.1 KB
+      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_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 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_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 36
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.3 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [8.0 MB-16.0 MB]: 564 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 14.1 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 564 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.3 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 1.3 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 31 frames, [64.0 KB-128.0 KB]: 532 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: [1.0 MB-2.0 MB]: 173 frames, [2.0 MB-4.0 MB]: 391 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.4 MB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 4
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.3 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [1.0 MB-2.0 MB]: 564 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]: 563 frames, [4.0 MB-8.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 2
+      Peak Allocated memory 5.2 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 1.3 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 564 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]: 564 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.7 KB
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -0,0 +1,377 @@
+{
+    "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 2.8396008014678955,
+            "min": 2.8396008014678955,
+            "max": 2.8736937046051025,
+            "count": 2
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 29361.47265625,
+            "min": 29361.47265625,
+            "max": 29524.328125,
+            "count": 2
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 19992.0,
+            "min": 9952.0,
+            "max": 19992.0,
+            "count": 2
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 19992.0,
+            "min": 9952.0,
+            "max": 19992.0,
+            "count": 2
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 1.263075828552246,
+            "min": 0.4022206962108612,
+            "max": 1.263075828552246,
+            "count": 2
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 258.9305419921875,
+            "min": 78.03081512451172,
+            "max": 258.9305419921875,
+            "count": 2
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 2
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 10945.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 2
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06481831646798289,
+            "min": 0.06481831646798289,
+            "max": 0.07193488530630894,
+            "count": 2
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.3240915823399144,
+            "min": 0.28773954122523576,
+            "max": 0.3240915823399144,
+            "count": 2
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.19746566072982902,
+            "min": 0.09731209359255016,
+            "max": 0.19746566072982902,
+            "count": 2
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 0.987328303649145,
+            "min": 0.38924837437020066,
+            "max": 0.987328303649145,
+            "count": 2
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 7.032007656e-05,
+            "min": 7.032007656e-05,
+            "max": 0.00021882002706000002,
+            "count": 2
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 0.0003516003828,
+            "min": 0.0003516003828,
+            "max": 0.0008752801082400001,
+            "count": 2
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.12344000000000002,
+            "min": 0.12344000000000002,
+            "max": 0.17294,
+            "count": 2
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.6172000000000001,
+            "min": 0.6172000000000001,
+            "max": 0.69176,
+            "count": 2
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.0011796560000000003,
+            "min": 0.0011796560000000003,
+            "max": 0.003649706,
+            "count": 2
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.005898280000000001,
+            "min": 0.005898280000000001,
+            "max": 0.014598824,
+            "count": 2
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 5.745454545454545,
+            "min": 2.8636363636363638,
+            "max": 5.745454545454545,
+            "count": 2
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 316.0,
+            "min": 126.0,
+            "max": 316.0,
+            "count": 2
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 5.745454545454545,
+            "min": 2.8636363636363638,
+            "max": 5.745454545454545,
+            "count": 2
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 316.0,
+            "min": 126.0,
+            "max": 316.0,
+            "count": 2
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 2
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 2
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1692016966",
+        "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
+        "command_line_arguments": "/home/victor/.local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1",
+        "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": "1692017019"
+    },
+    "total": 53.44478477200005,
+    "count": 1,
+    "self": 1.2209125869999298,
+    "children": {
+        "run_training.setup": {
+            "total": 0.02174069300008341,
+            "count": 1,
+            "self": 0.02174069300008341
+        },
+        "TrainerController.start_learning": {
+            "total": 52.202131492000035,
+            "count": 1,
+            "self": 0.07423351099873798,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 6.655812728000001,
+                    "count": 1,
+                    "self": 6.655812728000001
+                },
+                "TrainerController.advance": {
+                    "total": 45.364935828001535,
+                    "count": 1879,
+                    "self": 0.021415703004322495,
+                    "children": {
+                        "env_step": {
+                            "total": 45.34352012499721,
+                            "count": 1879,
+                            "self": 29.21571261499139,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 16.105558508004606,
+                                    "count": 1879,
+                                    "self": 0.1321435220006606,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 15.973414986003945,
+                                            "count": 1879,
+                                            "self": 15.973414986003945
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.022249002001217377,
+                                    "count": 1879,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 52.006834045000915,
+                                            "count": 1879,
+                                            "is_parallel": true,
+                                            "self": 30.296384265993538,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0020248989999345213,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005751999999574764,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0014496989999770449,
+                                                                    "count": 10,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0014496989999770449
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.019341898999982732,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0002630000001317967,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00017419999994672253,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00017419999994672253
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.01802319900002658,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.01802319900002658
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0008814999998776329,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00018149999959859997,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.000700000000279033,
+                                                                            "count": 10,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.000700000000279033
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 21.710449779007376,
+                                                    "count": 1878,
+                                                    "is_parallel": true,
+                                                    "self": 0.522955083021543,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 0.3177918349997526,
+                                                            "count": 1878,
+                                                            "is_parallel": true,
+                                                            "self": 0.3177918349997526
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 19.193862417992932,
+                                                            "count": 1878,
+                                                            "is_parallel": true,
+                                                            "self": 19.193862417992932
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 1.6758404429931488,
+                                                            "count": 1878,
+                                                            "is_parallel": true,
+                                                            "self": 0.36650654699997176,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 1.309333895993177,
+                                                                    "count": 18780,
+                                                                    "is_parallel": true,
+                                                                    "self": 1.309333895993177
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 0.00019559999986995535,
+                    "count": 1,
+                    "self": 0.00019559999986995535,
+                    "children": {
+                        "thread_root": {
+                            "total": 0.0,
+                            "count": 0,
+                            "is_parallel": true,
+                            "self": 0.0,
+                            "children": {
+                                "trainer_advance": {
+                                    "total": 45.22216580798954,
+                                    "count": 31251,
+                                    "is_parallel": true,
+                                    "self": 0.5188741819702045,
+                                    "children": {
+                                        "process_trajectory": {
+                                            "total": 26.509791286019208,
+                                            "count": 31251,
+                                            "is_parallel": true,
+                                            "self": 25.827423473019508,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 0.6823678129997006,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 0.6823678129997006
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 18.193500340000128,
+                                            "count": 9,
+                                            "is_parallel": true,
+                                            "self": 3.1610006109995084,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 15.03249972900062,
+                                                    "count": 456,
+                                                    "is_parallel": true,
+                                                    "self": 15.03249972900062
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.10695382499989137,
+                    "count": 1,
+                    "self": 0.0006624999998621206,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.10629132500002925,
+                            "count": 1,
+                            "self": 0.10629132500002925
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,56 @@
+{
+    "SnowballTarget": {
+        "checkpoints": [
+            {
+                "steps": 9952,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-9952.onnx",
+                "reward": 3.727272727272727,
+                "creation_time": 1692016995.2054837,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-9952.pt"
+                ]
+            },
+            {
+                "steps": 14992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-14992.onnx",
+                "reward": 4.454545454545454,
+                "creation_time": 1692017006.1288955,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-14992.pt"
+                ]
+            },
+            {
+                "steps": 19992,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-19992.onnx",
+                "reward": 7.181818181818182,
+                "creation_time": 1692017018.2311976,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-19992.pt"
+                ]
+            },
+            {
+                "steps": 20376,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-20376.onnx",
+                "reward": 7.181818181818182,
+                "creation_time": 1692017018.3880682,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-20376.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 20376,
+            "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
+            "reward": 7.181818181818182,
+            "creation_time": 1692017018.3880682,
+            "auxillary_file_paths": [
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-20376.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}