First Push

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e02400839a86a2611c9c26dc702e9e5ca28b24d7473c9b5f4ce13df16ca04ec
+size 1420238

Pyramids/Pyramids-1000032.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e02400839a86a2611c9c26dc702e9e5ca28b24d7473c9b5f4ce13df16ca04ec
+size 1420238

Pyramids/Pyramids-1000032.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2627ebdca66384e7fd94537f1eab57d2f719b2bc328d48dd9fe914f1128d8d45
+size 8655643

Pyramids/Pyramids-499954.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17079fc47def5a417e5504382a89b668891e792b1fd0004749ca9564b2024344
+size 1420238

Pyramids/Pyramids-499954.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5a52e4e5b40c2b86fb2872f5bee6837a794ef8021fe704580b55eb6367f183e
+size 8655562

Pyramids/Pyramids-999916.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e02400839a86a2611c9c26dc702e9e5ca28b24d7473c9b5f4ce13df16ca04ec
+size 1420238

Pyramids/Pyramids-999916.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:468fe63da8f13294a69d2d4a0faecc5dd641b49526bfb3592478a90673baa265
+size 8655562

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13addcf580db519053f09f759fa87944d19c387cfd55ca00b54d3371b514076d
+size 8655157

Pyramids/events.out.tfevents.1761130417.DESKTOP-NHACM7A.897.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6346649e4d7f77322b77104b3bdaabd06833495c879ef9c1eda7573d726b26b
+size 333107

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: hung3r/ppo-Pyramids
+  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": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "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": 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": 0.01, "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": 1000000, "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, "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": "ppo", "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 +1,92 @@
+default_settings: null
+behaviors:
+  Pyramids:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.0003
+      beta: 0.01
+      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: 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: 0.01
+        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: 1000000
+    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
+  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: ppo
+  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 +1,368 @@
+Mono path[0] = '/home/kali/HFRLCourse/unit5/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
+Mono config path = '/home/kali/HFRLCourse/unit5/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
+Found 2 interfaces on host : 0) 10.255.255.254 1) 172.22.38.139
+Multi-casting "[IP] 10.255.255.254 [Port] 55163 [Flags] 2 [Guid] 3856764701 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.22.38.139) [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': 1920x1080 (primary device).
+Desktop is 1920 x 1080 @ 60 Hz
+Invalid initial resolution 84 x 84 - forcing to 100 x 100
+Initialize engine version: 2021.3.5f1 (40eb3a945986)
+[Subsystems] Discovering subsystems at path /home/kali/HFRLCourse/unit5/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
+GfxDevice: creating device client; threaded=1; jobified=0
+Renderer: llvmpipe (LLVM 19.1.7, 256 bits)
+Vendor:   Mesa
+Version:  4.5 (Core Profile) Mesa 25.0.7-2
+GLES:     0
+ GL_3DFX_texture_compression_FXT1 GL_AMD_conservative_depth GL_AMD_draw_buffers_blend GL_AMD_gpu_shader_int64 GL_AMD_multi_draw_indirect GL_AMD_pinned_memory GL_AMD_query_buffer_object GL_AMD_seamless_cubemap_per_texture 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_2_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_conditional_render_inverted GL_ARB_conservative_depth GL_ARB_copy_buffer GL_ARB_copy_image GL_ARB_cull_distance GL_ARB_debug_output GL_ARB_depth_buffer_float GL_ARB_depth_clamp GL_ARB_derivative_control GL_ARB_direct_state_access GL_ARB_draw_buffers GL_A
+RB_draw_buffers_blend GL_ARB_draw_elements_base_vertex GL_ARB_draw_indirect GL_ARB_draw_instanced GL_ARB_enhanced_layouts 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_gl_spirv 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_pipeline_statistics_query GL_ARB_pixel_buffer_object GL_ARB_point_sprite GL_ARB_polygon_offset_clamp GL_ARB_post_depth_coverage GL_ARB_program_interface_query GL_ARB_provoking_vertex GL
+_ARB_query_buffer_object GL_ARB_robust_buffer_access_behavior GL_ARB_robustness GL_ARB_sample_shading GL_ARB_sampler_objects GL_ARB_seamless_cube_map GL_ARB_seamless_cubemap_per_texture GL_ARB_separate_shader_objects GL_ARB_shader_atomic_counter_ops GL_ARB_shader_atomic_counters GL_ARB_shader_ballot GL_ARB_shader_bit_encoding GL_ARB_shader_clock GL_ARB_shader_draw_parameters GL_ARB_shader_group_vote GL_ARB_shader_image_load_store 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_image_samples GL_ARB_shader_texture_lod GL_ARB_shader_viewport_layer_array GL_ARB_shading_language_420pack GL_ARB_shading_language_include GL_ARB_shading_language_packing GL_ARB_spirv_extensions GL_ARB_stencil_texturing GL_ARB_sync GL_ARB_tessellation_shader GL_ARB_texture_barrier GL_ARB_texture_border_clamp GL_ARB_texture_buffer_object GL_ARB_texture_buffer_object_rgb32 GL_ARB_texture_buffer_range GL_A
+RB_texture_compression_bptc GL_ARB_texture_compression_rgtc GL_ARB_texture_cube_map_array GL_ARB_texture_filter_anisotropic GL_ARB_texture_filter_minmax GL_ARB_texture_float GL_ARB_texture_gather GL_ARB_texture_mirror_clamp_to_edge 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_texture_view GL_ARB_timer_query GL_ARB_transform_feedback2 GL_ARB_transform_feedback3 GL_ARB_transform_feedback_instanced GL_ARB_transform_feedback_overflow_query 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_ARM_shader_framebuffer_fetch_depth_stencil GL_ATI_blend
+_equation_separate GL_ATI_meminfo GL_ATI_texture_float GL_ATI_texture_mirror_once GL_EXT_EGL_image_storage GL_EXT_EGL_image_storage_compression 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_polygon_offset_clamp GL_EXT_provoking_vertex GL_EXT_shader_framebuffer_fetch GL_EXT_shader_framebuffer_fetch_non_coherent GL_EXT_shader_image_load_formatted 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_filter_minmax GL_EXT_texture_integer GL_EXT_texture_mirror_clamp GL_EXT_texture_sRGB GL_EXT_texture_sRGB_R8 GL_EXT_texture_sRGB_RG8 GL
+_EXT_texture_sRGB_decode GL_EXT_texture_shadow_lod GL_EXT_texture_shared_exponent GL_EXT_texture_snorm GL_EXT_texture_storage 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_INTEL_shader_atomic_float_minmax GL_KHR_blend_equation_advanced GL_KHR_blend_equation_advanced_coherent 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_framebuffer_flip_y GL_MESA_pack_invert GL_MESA_shader_integer_functions GL_MESA_texture_signed_rgba GL_NVX_gpu_memory_info GL_NV_alpha_to_coverage_dither_control GL_NV_conditional_render GL_NV_copy_image GL_NV_depth_clamp GL_NV_packed_depth_stencil GL_NV_shader_atomic_float GL_NV_texture_barrier GL_OES_EGL_image GL_OVR_multiview GL_OVR_multiview2 GL_S3_s3tc
+OPENGL LOG: Creating OpenGL 4.5 graphics device ; Context level  <OpenGL 4.5> ; Context handle 305112976
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.075 seconds
+Default vsync count 1
+requesting resize 84 x 84
+resizing window to 84 x 84
+Desktop is 1920 x 1080 @ 60 Hz
+UnloadTime: 0.971534 ms
+Setting up 6 worker threads for Enlighten.
+requesting resize 84 x 84
+resizing window to 84 x 84
+Desktop is 1920 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]: 3793 frames, [32.0 KB-64.0 KB]: 12128 frames, [64.0 KB-128.0 KB]: 2845 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_Job.Worker 8]
+      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 1]
+      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 10]
+      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 251.5 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 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 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 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 6]
+      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 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 9]
+      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 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      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 12.0 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 12.0 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: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18468 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 13291
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.9 MB
+      Failed Allocations. Bucket layout:
+        16B: 26 Subsections = 8874 buckets. Failed count: 0
+        32B: 13 Subsections = 3328 buckets. Failed count: 0
+        48B: 55 Subsections = 11264 buckets. Failed count: 0
+        64B: 40 Subsections = 6826 buckets. Failed count: 8394
+        80B: 41 Subsections = 5997 buckets. Failed count: 5034
+        96B: 34 Subsections = 4352 buckets. Failed count: 35825
+        112B: 31 Subsections = 3527 buckets. Failed count: 0
+        128B: 16 Subsections = 1638 buckets. Failed count: 12897
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 501 frames, [32.0 MB-64.0 MB]: 18266 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 3
+      Peak Allocated memory 38.6 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18767 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 29.4 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
+      Failed Allocations. Bucket layout:
+        16B: 26 Subsections = 8874 buckets. Failed count: 0
+        32B: 13 Subsections = 3328 buckets. Failed count: 0
+        48B: 55 Subsections = 11264 buckets. Failed count: 0
+        64B: 40 Subsections = 6826 buckets. Failed count: 8394
+        80B: 41 Subsections = 5997 buckets. Failed count: 5034
+        96B: 34 Subsections = 4352 buckets. Failed count: 35825
+        112B: 31 Subsections = 3527 buckets. Failed count: 0
+        128B: 16 Subsections = 1638 buckets. Failed count: 12897
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18766 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]: 18767 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 69.0 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
+      Failed Allocations. Bucket layout:
+        16B: 26 Subsections = 8874 buckets. Failed count: 0
+        32B: 13 Subsections = 3328 buckets. Failed count: 0
+        48B: 55 Subsections = 11264 buckets. Failed count: 0
+        64B: 40 Subsections = 6826 buckets. Failed count: 8394
+        80B: 41 Subsections = 5997 buckets. Failed count: 5034
+        96B: 34 Subsections = 4352 buckets. Failed count: 35825
+        112B: 31 Subsections = 3527 buckets. Failed count: 0
+        128B: 16 Subsections = 1638 buckets. Failed count: 12897
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18767 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]: 18766 frames, [8.0 MB-16.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 3
+      Peak Allocated memory 9.1 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 1.9 MB
+      Failed Allocations. Bucket layout:
+        16B: 26 Subsections = 8874 buckets. Failed count: 0
+        32B: 13 Subsections = 3328 buckets. Failed count: 0
+        48B: 55 Subsections = 11264 buckets. Failed count: 0
+        64B: 40 Subsections = 6826 buckets. Failed count: 8394
+        80B: 41 Subsections = 5997 buckets. Failed count: 5034
+        96B: 34 Subsections = 4352 buckets. Failed count: 35825
+        112B: 31 Subsections = 3527 buckets. Failed count: 0
+        128B: 16 Subsections = 1638 buckets. Failed count: 12897
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 18767 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]: 18767 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: [32.0 KB-64.0 KB]: 18767 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 39.2 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":1761131659407,"processId":934,"allocatedMemory":2374001,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":407434},{"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":3506},{"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 +1,398 @@
+{
+    "name": "root",
+    "gauges": {
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.5119559168815613,
+            "min": 0.5034074187278748,
+            "max": 1.4569073915481567,
+            "count": 33
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 15391.443359375,
+            "min": 14965.294921875,
+            "max": 44196.7421875,
+            "count": 33
+        },
+        "Pyramids.Step.mean": {
+            "value": 989962.0,
+            "min": 29952.0,
+            "max": 989962.0,
+            "count": 33
+        },
+        "Pyramids.Step.sum": {
+            "value": 989962.0,
+            "min": 29952.0,
+            "max": 989962.0,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.4965977966785431,
+            "min": -0.10757958143949509,
+            "max": 0.5024316310882568,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 135.57119750976562,
+            "min": -25.926679611206055,
+            "max": 138.168701171875,
+            "count": 33
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": 0.14437216520309448,
+            "min": -0.05144139751791954,
+            "max": 0.2575911283493042,
+            "count": 33
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": 39.41360092163086,
+            "min": -14.043501853942871,
+            "max": 62.33705520629883,
+            "count": 33
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06429459458592114,
+            "min": 0.06290810950304399,
+            "max": 0.0730116966252262,
+            "count": 33
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.900124324202896,
+            "min": 0.49941473010805,
+            "max": 1.0316345880079705,
+            "count": 33
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.01575176536780342,
+            "min": 0.0006719232966448452,
+            "max": 0.016589767467285996,
+            "count": 33
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.2205247151492479,
+            "min": 0.0073911562630932974,
+            "max": 0.23225674454200393,
+            "count": 33
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 7.292690426278571e-06,
+            "min": 7.292690426278571e-06,
+            "max": 0.00029515063018788575,
+            "count": 33
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 0.00010209766596789999,
+            "min": 0.00010209766596789999,
+            "max": 0.0032539844153385996,
+            "count": 33
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10243086428571431,
+            "min": 0.10243086428571431,
+            "max": 0.19838354285714285,
+            "count": 33
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4340321000000003,
+            "min": 1.3886848,
+            "max": 2.4016496,
+            "count": 33
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.00025284334214285717,
+            "min": 0.00025284334214285717,
+            "max": 0.00983851593142857,
+            "count": 33
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.0035398067900000007,
+            "min": 0.0035398067900000007,
+            "max": 0.10848767386000001,
+            "count": 33
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.006991219241172075,
+            "min": 0.006991219241172075,
+            "max": 0.430558443069458,
+            "count": 33
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.09787707030773163,
+            "min": 0.09787707030773163,
+            "max": 3.013909101486206,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 394.2987012987013,
+            "min": 344.4318181818182,
+            "max": 999.0,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 30361.0,
+            "min": 15984.0,
+            "max": 32663.0,
+            "count": 33
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.4757895884769303,
+            "min": -1.0000000521540642,
+            "max": 1.6100999810309573,
+            "count": 33
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 113.63579831272364,
+            "min": -30.359001725912094,
+            "max": 141.68879833072424,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.4757895884769303,
+            "min": -1.0000000521540642,
+            "max": 1.6100999810309573,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 113.63579831272364,
+            "min": -30.359001725912094,
+            "max": 141.68879833072424,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.028597743684908243,
+            "min": 0.02780689784611406,
+            "max": 9.7458865782246,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 2.2020262637379346,
+            "min": 2.2020262637379346,
+            "max": 155.9341852515936,
+            "count": 33
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 33
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 33
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1761130414",
+        "python_version": "3.10.18 (main, Sep  2 2025, 14:19:37) [Clang 20.1.4 ]",
+        "command_line_arguments": "/home/kali/HFRLCourse/unit5/.venv/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --force",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.8.0+cpu",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1761131659"
+    },
+    "total": 1244.615810724,
+    "count": 1,
+    "self": 0.2694132350000018,
+    "children": {
+        "run_training.setup": {
+            "total": 0.013962421999963226,
+            "count": 1,
+            "self": 0.013962421999963226
+        },
+        "TrainerController.start_learning": {
+            "total": 1244.332435067,
+            "count": 1,
+            "self": 0.8393597730209876,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 4.279692654000087,
+                    "count": 1,
+                    "self": 4.279692654000087
+                },
+                "TrainerController.advance": {
+                    "total": 1239.177523711979,
+                    "count": 63612,
+                    "self": 0.6828005569375364,
+                    "children": {
+                        "env_step": {
+                            "total": 947.8981407069955,
+                            "count": 63612,
+                            "self": 898.6912184359851,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 48.66240158897756,
+                                    "count": 63612,
+                                    "self": 1.9695368339429251,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 46.692864755034634,
+                                            "count": 62554,
+                                            "self": 46.692864755034634
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.5445206820328394,
+                                    "count": 63612,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 1242.009381177011,
+                                            "count": 63612,
+                                            "is_parallel": true,
+                                            "self": 396.22949405805855,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.001819523999984085,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006689489998734643,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0011505750001106207,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0011505750001106207
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.028025157000001855,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0001569569999446685,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00015895100000307139,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00015895100000307139
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.026012844999968365,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.026012844999968365
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0016964040000857494,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00014630800035320135,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.001550095999732548,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.001550095999732548
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 845.7798871189524,
+                                                    "count": 63611,
+                                                    "is_parallel": true,
+                                                    "self": 9.647923194920963,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 7.677414510994026,
+                                                            "count": 63611,
+                                                            "is_parallel": true,
+                                                            "self": 7.677414510994026
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 798.7448140880049,
+                                                            "count": 63611,
+                                                            "is_parallel": true,
+                                                            "self": 798.7448140880049
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 29.70973532503251,
+                                                            "count": 63611,
+                                                            "is_parallel": true,
+                                                            "self": 7.056422167005735,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 22.653313158026776,
+                                                                    "count": 508888,
+                                                                    "is_parallel": true,
+                                                                    "self": 22.653313158026776
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 290.596582448046,
+                            "count": 63612,
+                            "self": 1.5125231610353467,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 55.1328491810076,
+                                    "count": 63612,
+                                    "self": 54.99991200400757,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.13293717700003072,
+                                            "count": 2,
+                                            "self": 0.13293717700003072
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 233.95121010600303,
+                                    "count": 441,
+                                    "self": 120.07437019402391,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 113.87683991197912,
+                                            "count": 22812,
+                                            "self": 113.87683991197912
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 6.610000582440989e-07,
+                    "count": 1,
+                    "self": 6.610000582440989e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.03585826699986683,
+                    "count": 1,
+                    "self": 0.0018302670000593935,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.034027999999807435,
+                            "count": 1,
+                            "self": 0.034027999999807435
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,47 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 499954,
+                "file_path": "results/ppo/Pyramids/Pyramids-499954.onnx",
+                "reward": -0.9995000511407852,
+                "creation_time": 1761131030.1286676,
+                "auxillary_file_paths": [
+                    "results/ppo/Pyramids/Pyramids-499954.pt"
+                ]
+            },
+            {
+                "steps": 999916,
+                "file_path": "results/ppo/Pyramids/Pyramids-999916.onnx",
+                "reward": 0.8638666470845541,
+                "creation_time": 1761131659.173305,
+                "auxillary_file_paths": [
+                    "results/ppo/Pyramids/Pyramids-999916.pt"
+                ]
+            },
+            {
+                "steps": 1000032,
+                "file_path": "results/ppo/Pyramids/Pyramids-1000032.onnx",
+                "reward": 1.1191499829292297,
+                "creation_time": 1761131659.2126522,
+                "auxillary_file_paths": [
+                    "results/ppo/Pyramids/Pyramids-1000032.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1000032,
+            "file_path": "results/ppo/Pyramids.onnx",
+            "reward": 1.1191499829292297,
+            "creation_time": 1761131659.2126522,
+            "auxillary_file_paths": [
+                "results/ppo/Pyramids/Pyramids-1000032.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.8.0+cpu"
+    }
+}