Add PyramidsRND PPO trained model

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ab2087143bc425411b4688abc09ededfb5f432b85fd7b9ee6a5f8f7523b5e77
+size 1420238

Pyramids/Pyramids-1000007.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ab2087143bc425411b4688abc09ededfb5f432b85fd7b9ee6a5f8f7523b5e77
+size 1420238

Pyramids/Pyramids-1000007.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:911e88dee101f5254c091d4d0f93619eb7d79e62c442acdc5a3021a766b4f987
+size 8656079

Pyramids/Pyramids-499919.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e28067ad910bc7e967a4b2a72707c2863f3ba145eeb16c23ab8deb0bfcf8da5
+size 1420238

Pyramids/Pyramids-499919.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e02e9b8613fa17de4eb024125cdd5134eae2547204e442bc053f22a7db1f8125
+size 8656000

Pyramids/Pyramids-999879.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ab2087143bc425411b4688abc09ededfb5f432b85fd7b9ee6a5f8f7523b5e77
+size 1420238

Pyramids/Pyramids-999879.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee232abd2b77bcbc4f78fa8f9d68c6c49622b10cda017302b580a573686658c4
+size 8656000

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:373428581a418a48850f1187c54a84812357f478c8840a11ebc2fc7a1d8427fa
+size 8655605

Pyramids/events.out.tfevents.1781433660.archlinux.124999.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0b01f8fcf0633169c5bb2c5b78c048ae66da0175e967a15db2011144a2a464f
+size 314252

Pyramids/events.out.tfevents.1781434906.archlinux.129560.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3449a9a9f8bf7cef0ec2dedc0aec60bae6e8a328826f46fdd01242c9d37ecf6a
+size 1423

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: KrishBakshi/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/Pyramids/Pyramids/Pyramids", "env_args": ["-screen-fullscreen", "1"], "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": 1280, "height": 720, "quality_level": 5, "time_scale": 1.0, "target_frame_rate": 30, "capture_frame_rate": 30, "no_graphics": false, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "PyramidsRND_v1", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": true, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,94 @@
+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/Pyramids/Pyramids/Pyramids
+  env_args:
+  - -screen-fullscreen
+  - '1'
+  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: 1280
+  height: 720
+  quality_level: 5
+  time_scale: 1.0
+  target_frame_rate: 30
+  capture_frame_rate: 30
+  no_graphics: false
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: PyramidsRND_v1
+  initialize_from: null
+  load_model: false
+  resume: true
+  force: false
+  train_model: false
+  inference: true
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,36 @@
+Mono path[0] = '/home/krish/wrk/ml-agents/training-envs-executables/Pyramids/Pyramids/Pyramids_Data/Managed'
+Mono config path = '/home/krish/wrk/ml-agents/training-envs-executables/Pyramids/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
+Found 2 interfaces on host : 0) 192.168.1.15 1) 192.168.1.12
+Multi-casting "[IP] 192.168.1.15 [Port] 55310 [Flags] 2 [Guid] 308980634 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,192.168.1.15) [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 'screen': 1280x720 (primary device).
+Desktop is 1280 x 720 @ 0 Hz
+Initialize engine version: 2021.3.5f1 (40eb3a945986)
+[Subsystems] Discovering subsystems at path /home/krish/wrk/ml-agents/training-envs-executables/Pyramids/Pyramids/Pyramids_Data/UnitySubsystems
+GfxDevice: creating device client; threaded=1; jobified=0
+Renderer: llvmpipe (LLVM 22.1.1, 256 bits)
+Vendor:   Mesa
+Version:  4.5 (Core Profile) Mesa 26.0.3-arch1.1
+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_locations 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_t
+exture_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_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_de
+pth_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_depth_bounds_test 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_clock 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_sample_locations GL_NV_shader_atomic_float GL_NV_texture_barrier GL_OES_EGL_image GL_OV
+R_multiview GL_OVR_multiview2 GL_S3_s3tc
+OPENGL LOG: Creating OpenGL 4.5 graphics device ; Context level  <OpenGL 4.5> ; Context handle 991563424
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.054 seconds
+Default vsync count 1
+requesting resize 1280 x 720
+Using native desktop resolution 1280 x 720
+requesting fullscreen 1280 x 720 at 0 Hz
+Desktop is 1280 x 720 @ 0 Hz
+UnloadTime: 0.855434 ms
+Setting up 8 worker threads for Enlighten.
+requesting resize 1280 x 720
+resizing window to 1280 x 720
+Desktop is 1280 x 720 @ 0 Hz
+X connection to :99 broken (explicit kill or server shutdown).

run_logs/timers.json

@@ -0,0 +1,185 @@
+{
+    "name": "root",
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1781434903",
+        "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
+        "command_line_arguments": "/home/krish/miniconda3/envs/rl/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/Pyramids/Pyramids/Pyramids --run-id=PyramidsRND_v1 --inference --resume --width=1280 --height=720 --time-scale=1 --target-frame-rate=30 --capture-frame-rate=30 --env-args -screen-fullscreen 1",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.8.0+cu128",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1781434987"
+    },
+    "total": 83.93240248897928,
+    "count": 1,
+    "self": 0.04536691302200779,
+    "children": {
+        "run_training.setup": {
+            "total": 0.014802956982748583,
+            "count": 1,
+            "self": 0.014802956982748583
+        },
+        "TrainerController.start_learning": {
+            "total": 83.87223261897452,
+            "count": 1,
+            "self": 0.03179568875930272,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 4.284268685005372,
+                    "count": 1,
+                    "self": 4.284268685005372
+                },
+                "TrainerController.advance": {
+                    "total": 79.55616718321107,
+                    "count": 1183,
+                    "self": 0.02702596431481652,
+                    "children": {
+                        "env_step": {
+                            "total": 77.83172014908632,
+                            "count": 1183,
+                            "self": 74.95250500791008,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 2.8602947444014717,
+                                    "count": 1183,
+                                    "self": 0.08303508427343331,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 2.7772596601280384,
+                                            "count": 1149,
+                                            "self": 2.7772596601280384
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.018920396774774417,
+                                    "count": 1182,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 83.80282710303436,
+                                            "count": 1182,
+                                            "is_parallel": true,
+                                            "self": 11.380317655974068,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0011298650060780346,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00031689307070337236,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0008129719353746623,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0008129719353746623
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.11441023799125105,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0003504969645291567,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00021565300994552672,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00021565300994552672
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.11249973101075739,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.11249973101075739
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0013443570060189813,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00021412002388387918,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0011302369821351022,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0011302369821351022
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 72.42250944706029,
+                                                    "count": 1181,
+                                                    "is_parallel": true,
+                                                    "self": 0.4916796865290962,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 0.3221646789170336,
+                                                            "count": 1181,
+                                                            "is_parallel": true,
+                                                            "self": 0.3221646789170336
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 70.39682772691594,
+                                                            "count": 1181,
+                                                            "is_parallel": true,
+                                                            "self": 70.39682772691594
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 1.2118373546982184,
+                                                            "count": 1181,
+                                                            "is_parallel": true,
+                                                            "self": 0.2656794083013665,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.9461579463968519,
+                                                                    "count": 9448,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.9461579463968519
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 1.6974210698099341,
+                            "count": 1182,
+                            "self": 0.0619773285870906,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 1.6354437412228435,
+                                    "count": 1182,
+                                    "self": 1.6354437412228435
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.0619987733662128e-06,
+                    "count": 1,
+                    "self": 1.0619987733662128e-06
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,47 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 499919,
+                "file_path": "results/PyramidsRND_v1/Pyramids/Pyramids-499919.onnx",
+                "reward": null,
+                "creation_time": 1781434213.5734684,
+                "auxillary_file_paths": [
+                    "results/PyramidsRND_v1/Pyramids/Pyramids-499919.pt"
+                ]
+            },
+            {
+                "steps": 999879,
+                "file_path": "results/PyramidsRND_v1/Pyramids/Pyramids-999879.onnx",
+                "reward": 1.6865000029404957,
+                "creation_time": 1781434829.881059,
+                "auxillary_file_paths": [
+                    "results/PyramidsRND_v1/Pyramids/Pyramids-999879.pt"
+                ]
+            },
+            {
+                "steps": 1000007,
+                "file_path": "results/PyramidsRND_v1/Pyramids/Pyramids-1000007.onnx",
+                "reward": 1.6865000029404957,
+                "creation_time": 1781434829.9428637,
+                "auxillary_file_paths": [
+                    "results/PyramidsRND_v1/Pyramids/Pyramids-1000007.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1000007,
+            "file_path": "results/PyramidsRND_v1/Pyramids.onnx",
+            "reward": 1.6865000029404957,
+            "creation_time": 1781434829.9428637,
+            "auxillary_file_paths": [
+                "results/PyramidsRND_v1/Pyramids/Pyramids-1000007.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.8.0+cu128"
+    }
+}