first test commit

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16460465a48d55b9a8768376f292ec39c7b708b392db34731dd6321d220261ea
+size 1418184

Pyramids/Pyramids-100003.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16460465a48d55b9a8768376f292ec39c7b708b392db34731dd6321d220261ea
+size 1418184

Pyramids/Pyramids-100003.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17a3646c0f2d7688b98d3be5753c410cb236ba237aa6dd46d27273e921ef65f2
+size 8650990

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17a3646c0f2d7688b98d3be5753c410cb236ba237aa6dd46d27273e921ef65f2
+size 8650990

Pyramids/events.out.tfevents.1692017720.DESKTOP-9GKAG7F.1552.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e319d97640786bbf36dd9cec2c3f39ca4c79d9a4c89f096bde1c185a744c1cc5
+size 22916

README.md

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

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 248, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 5, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "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}}, "rnd": {"gamma": 0.99, "strength": 0.05, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 100000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "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": "Pyramids Training", "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 +1,90 @@
+default_settings: null
+behaviors:
+  Pyramids:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 248
+      buffer_size: 2048
+      learning_rate: 0.0003
+      beta: 0.01
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 5
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 500000
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      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
+      rnd:
+        gamma: 0.99
+        strength: 0.05
+        network_settings:
+          normalize: false
+          hidden_units: 64
+          num_layers: 3
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+        learning_rate: 0.0001
+        encoding_size: null
+    init_path: null
+    keep_checkpoints: 5
+    even_checkpoints: false
+    max_steps: 100000
+    time_horizon: 128
+    summary_freq: 30000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/linux/Pyramids/Pyramids
+  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: Pyramids Training
+  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 +1,313 @@
+Mono path[0] = '/home/victor/pythonprojects/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
+Mono config path = '/home/victor/pythonprojects/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
+Found 1 interfaces on host : 0) 172.24.50.6
+Multi-casting "[IP] 172.24.50.6 [Port] 55384 [Flags] 2 [Guid] 3686515790 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.24.50.6) [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': 2560x1080 (primary device).
+Display 1 'XWAYLAND1 27"': 1920x1080 (secondary device).
+Desktop is 2560 x 1080 @ 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 /home/victor/pythonprojects/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
+GfxDevice: creating device client; threaded=1; jobified=0
+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 28617968
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.066 seconds
+Default vsync count 1
+requesting resize 80 x 80
+resizing window to 80 x 80
+Desktop is 2560 x 1080 @ 60 Hz
+Desktop is 2560 x 1080 @ 60 Hz
+UnloadTime: 0.836900 ms
+Setting up 4 worker threads for Enlighten.
+requesting resize 84 x 84
+resizing window to 84 x 84
+Desktop is 2560 x 1080 @ 60 Hz
+PlayerConnection::CleanupMemory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [16.0 KB-32.0 KB]: 1175 frames, [32.0 KB-64.0 KB]: 643 frames, [64.0 KB-128.0 KB]: 71 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 12.0 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_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_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 12.0 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 320.0 KB
+      Peak Allocated Bytes 251.6 KB
+      Overflow Count 4
+    [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 0.9 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 12.0 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 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 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 12.0 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 12.0 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 12.0 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 12.0 KB
+      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_UnityGfxDeviceWorker]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 45.0 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_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: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 1591 frames
+  Requested Block Size 1.0 MB
+  Peak Block count 2
+  Peak Allocated memory 1.6 MB
+  Peak Large allocation bytes 0 B
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 11816
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.9 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 1877 frames, [32.0 MB-64.0 MB]: 13 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 3
+      Peak Allocated memory 38.0 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 1890 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 27.1 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 4
+  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 1.9 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 1889 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]: 1890 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 74.9 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 1
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.9 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [1.0 MB-2.0 MB]: 1890 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.8 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_CACHEOBJECTS_THREAD]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 1890 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 2
+      Peak Allocated memory 7.0 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 1.9 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 1890 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]: 1890 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.9 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_PROFILER]
+  Peak usage frame count: [16.0 KB-32.0 KB]: 1 frames, [32.0 KB-64.0 KB]: 1889 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 34.6 KB
+  Peak Large allocation bytes 0 B
+    [ALLOC_PROFILER_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 396 B
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1692017912384,"processId":1584,"allocatedMemory":2093101,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":130484},{"Thread":34756},{"Manager":14031},{"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":3540},{"DynamicArray":30872},{"HashMap":7680},{"Utility":3808},{"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 +1,391 @@
+{
+    "name": "root",
+    "gauges": {
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.5920994281768799,
+            "min": 0.5920994281768799,
+            "max": 1.396640419960022,
+            "count": 3
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 17772.45703125,
+            "min": 17772.45703125,
+            "max": 42368.484375,
+            "count": 3
+        },
+        "Pyramids.Step.mean": {
+            "value": 89895.0,
+            "min": 29952.0,
+            "max": 89895.0,
+            "count": 3
+        },
+        "Pyramids.Step.sum": {
+            "value": 89895.0,
+            "min": 29952.0,
+            "max": 89895.0,
+            "count": 3
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.08060117810964584,
+            "min": -0.08060117810964584,
+            "max": 0.1492552012205124,
+            "count": 3
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -19.50548553466797,
+            "min": -19.50548553466797,
+            "max": 35.37348175048828,
+            "count": 3
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": 0.910521388053894,
+            "min": 0.910521388053894,
+            "max": 1.4801007509231567,
+            "count": 3
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": 220.34617614746094,
+            "min": 220.34617614746094,
+            "max": 356.70428466796875,
+            "count": 3
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.04922671732786335,
+            "min": 0.04922671732786335,
+            "max": 0.05336748282426961,
+            "count": 3
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.5907206079343602,
+            "min": 0.3735723797698873,
+            "max": 0.5907206079343602,
+            "count": 3
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.002812625459016786,
+            "min": 0.002812625459016786,
+            "max": 0.058140459392761475,
+            "count": 3
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.03375150550820143,
+            "min": 0.03375150550820143,
+            "max": 0.40698321574933033,
+            "count": 3
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 7.774157408616665e-05,
+            "min": 7.774157408616665e-05,
+            "max": 0.0002515063018788571,
+            "count": 3
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 0.0009328988890339999,
+            "min": 0.0009328988890339999,
+            "max": 0.0017605441131519997,
+            "count": 3
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.12591383333333336,
+            "min": 0.12591383333333336,
+            "max": 0.1838354285714286,
+            "count": 3
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.5109660000000003,
+            "min": 1.2868480000000002,
+            "max": 1.5565020000000003,
+            "count": 3
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.0025987919500000006,
+            "min": 0.0025987919500000006,
+            "max": 0.008385159314285715,
+            "count": 3
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.031185503400000005,
+            "min": 0.031185503400000005,
+            "max": 0.0586961152,
+            "count": 3
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.12982051074504852,
+            "min": 0.12982051074504852,
+            "max": 0.4058314263820648,
+            "count": 3
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 1.557846188545227,
+            "min": 1.557846188545227,
+            "max": 2.840820074081421,
+            "count": 3
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 962.030303030303,
+            "min": 962.030303030303,
+            "max": 999.0,
+            "count": 3
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 31747.0,
+            "min": 15984.0,
+            "max": 31843.0,
+            "count": 3
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": -0.7204667153683576,
+            "min": -1.0000000521540642,
+            "max": -0.7204667153683576,
+            "count": 3
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": -23.7754016071558,
+            "min": -27.873001739382744,
+            "max": -16.000000834465027,
+            "count": 3
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": -0.7204667153683576,
+            "min": -1.0000000521540642,
+            "max": -0.7204667153683576,
+            "count": 3
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": -23.7754016071558,
+            "min": -27.873001739382744,
+            "max": -16.000000834465027,
+            "count": 3
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 7.310272389289104,
+            "min": 7.310272389289104,
+            "max": 37.97674008458853,
+            "count": 3
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 241.23898884654045,
+            "min": 241.23898884654045,
+            "max": 607.6278413534164,
+            "count": 3
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 3
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 3
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1692017717",
+        "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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --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": "1692017912"
+    },
+    "total": 195.31421026000044,
+    "count": 1,
+    "self": 0.3698744060006902,
+    "children": {
+        "run_training.setup": {
+            "total": 0.020221199999923556,
+            "count": 1,
+            "self": 0.020221199999923556
+        },
+        "TrainerController.start_learning": {
+            "total": 194.92411465399982,
+            "count": 1,
+            "self": 0.11492089701278019,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 5.843547811000008,
+                    "count": 1,
+                    "self": 5.843547811000008
+                },
+                "TrainerController.advance": {
+                    "total": 188.84464944398724,
+                    "count": 6309,
+                    "self": 0.107466295982249,
+                    "children": {
+                        "env_step": {
+                            "total": 118.0586339260035,
+                            "count": 6309,
+                            "self": 98.41974282002502,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 19.56722700800401,
+                                    "count": 6309,
+                                    "self": 0.40011209500471523,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 19.167114912999295,
+                                            "count": 6297,
+                                            "self": 19.167114912999295
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.07166409797446249,
+                                    "count": 6309,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 194.55289205097688,
+                                            "count": 6309,
+                                            "is_parallel": true,
+                                            "self": 103.75594365197367,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0013616999999612744,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0004546000000118511,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0009070999999494234,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0009070999999494234
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.03046879999965313,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00023869999995440594,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0002528999998503423,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0002528999998503423
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.028661299999839684,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.028661299999839684
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0013159000000086962,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00026789999992615776,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0010480000000825385,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0010480000000825385
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 90.79694839900321,
+                                                    "count": 6308,
+                                                    "is_parallel": true,
+                                                    "self": 1.5050858869885815,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 1.172996385992974,
+                                                            "count": 6308,
+                                                            "is_parallel": true,
+                                                            "self": 1.172996385992974
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 83.50352456999826,
+                                                            "count": 6308,
+                                                            "is_parallel": true,
+                                                            "self": 83.50352456999826
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 4.615341556023395,
+                                                            "count": 6308,
+                                                            "is_parallel": true,
+                                                            "self": 1.0762646860112,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 3.5390768700121953,
+                                                                    "count": 50464,
+                                                                    "is_parallel": true,
+                                                                    "self": 3.5390768700121953
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 70.6785492220015,
+                            "count": 6309,
+                            "self": 0.15120609997120482,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 9.888434483030323,
+                                    "count": 6309,
+                                    "self": 9.888434483030323
+                                },
+                                "_update_policy": {
+                                    "total": 60.638908638999965,
+                                    "count": 34,
+                                    "self": 34.277911250998386,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 26.36099738800158,
+                                            "count": 1910,
+                                            "self": 26.36099738800158
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 6.000000212225132e-07,
+                    "count": 1,
+                    "self": 6.000000212225132e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.12099590199977683,
+                    "count": 1,
+                    "self": 0.0012509999996836996,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.11974490200009313,
+                            "count": 1,
+                            "self": 0.11974490200009313
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,29 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 100003,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-100003.onnx",
+                "reward": null,
+                "creation_time": 1692017912.064484,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-100003.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 100003,
+            "file_path": "results/Pyramids Training/Pyramids.onnx",
+            "reward": null,
+            "creation_time": 1692017912.064484,
+            "auxillary_file_paths": [
+                "results/Pyramids Training/Pyramids/Pyramids-100003.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}