First Push

README.md

@@ -0,0 +1,29 @@
+---
+library_name: ml-agents
+tags:
+- SnowballTarget
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-SnowballTarget
+---
+
+ # **ppo** Agent playing **SnowballTarget**
+ This is a trained model of a **ppo** agent playing **SnowballTarget** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
+ 
+ ## Usage (with ML-Agents)
+ The Documentation: https://github.com/huggingface/ml-agents#get-started
+ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+
+
+ ### Resume the training
+ ```
+ 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. Go to https://huggingface.co/spaces/unity/ML-Agents-SnowballTarget
+ 2. Step 1: Find your model_id: Gaivoronsky/ppo-SnowballTargetTESTCOLAB
+ 3. Step 2: Select your *.nn /*.onnx file
+ 4. Click on Watch the agent play 👀
+ 

SnowballTarget.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b81b93c61110a453b465ee9177c6b9cd5e26128c4a1d359f7064a05f3eaca7cf
+size 646532

SnowballTarget/SnowballTarget-149984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5868745a6f950c187e9f9813d339e5da185c86ca9d441df84ebd0470b988449
+size 646532

SnowballTarget/SnowballTarget-149984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f078edb82663d1b12aa45224da3e7751562bb2006e0943129577cf38e4503932
+size 3843968

SnowballTarget/SnowballTarget-199984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b81b93c61110a453b465ee9177c6b9cd5e26128c4a1d359f7064a05f3eaca7cf
+size 646532

SnowballTarget/SnowballTarget-199984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6d6fb66a99e851fba846d1af5a633239ca32f4001635fb7a1f42d66eec4a34d
+size 3843968

SnowballTarget/SnowballTarget-200112.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b81b93c61110a453b465ee9177c6b9cd5e26128c4a1d359f7064a05f3eaca7cf
+size 646532

SnowballTarget/SnowballTarget-200112.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae702e09287279a7e98305b20e02f3f03b4840ef47785362d1ea0fbb7b49b942
+size 3843968

SnowballTarget/SnowballTarget-49936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:975660c976bcbe1144b0ec6538ce43e70746f46746fbba1fab93548e703a8c2b
+size 646532

SnowballTarget/SnowballTarget-49936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b09e9e126db402bf8599e7a0d67009ad46010e59e0dcbdb43a86d6f7749cb146
+size 3843968

SnowballTarget/SnowballTarget-99960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ae049f566ee8faa2f03a72f9ac3204409c4025a4d6aacbcf838541b00bb5fa7
+size 646532

SnowballTarget/SnowballTarget-99960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c3b488753f4be84948bc1a119ae91d8e2b48a5f871222d124c2dbbe8981bb1b
+size 3843968

SnowballTarget/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae702e09287279a7e98305b20e02f3f03b4840ef47785362d1ea0fbb7b49b942
+size 3843968

SnowballTarget/events.out.tfevents.1684854696.alex-pc.4289.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f1da8fe8e17fe429176e4320fab510562ccd592761190faf739bb97dc79725e
+size 23766

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 200000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SnowballTarget", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,77 @@
+default_settings: null
+behaviors:
+ SnowballTarget:
+ trainer_type: ppo
+ hyperparameters:
+ batch_size: 128
+ buffer_size: 2048
+ learning_rate: 0.0003
+ beta: 0.005
+ epsilon: 0.2
+ lambd: 0.95
+ num_epoch: 3
+ shared_critic: false
+ learning_rate_schedule: linear
+ beta_schedule: linear
+ epsilon_schedule: linear
+ checkpoint_interval: 50000
+ network_settings:
+ normalize: false
+ hidden_units: 256
+ num_layers: 2
+ vis_encode_type: simple
+ memory: null
+ goal_conditioning_type: hyper
+ deterministic: false
+ reward_signals:
+ extrinsic:
+ gamma: 0.99
+ strength: 1.0
+ network_settings:
+ normalize: false
+ hidden_units: 128
+ num_layers: 2
+ vis_encode_type: simple
+ memory: null
+ goal_conditioning_type: hyper
+ deterministic: false
+ init_path: null
+ keep_checkpoints: 10
+ even_checkpoints: false
+ max_steps: 200000
+ time_horizon: 64
+ summary_freq: 10000
+ threaded: true
+ self_play: null
+ behavioral_cloning: null
+env_settings:
+ env_path: ./training-envs-executables/linux/SnowballTarget/SnowballTarget
+ env_args: null
+ base_port: 5005
+ num_envs: 1
+ num_areas: 1
+ seed: -1
+ max_lifetime_restarts: 10
+ restarts_rate_limit_n: 1
+ restarts_rate_limit_period_s: 60
+engine_settings:
+ width: 84
+ height: 84
+ quality_level: 5
+ time_scale: 20
+ target_frame_rate: -1
+ capture_frame_rate: 60
+ no_graphics: false
+environment_parameters: null
+checkpoint_settings:
+ run_id: SnowballTarget
+ initialize_from: null
+ load_model: false
+ resume: false
+ force: false
+ train_model: false
+ inference: false
+ results_dir: results
+torch_settings:
+ device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,319 @@
+Mono path[0] = '/home/alex/Projects/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/Managed'
+Mono config path = '/home/alex/Projects/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+Display 0 'Mi Monitor 34"': 3440x1440 (primary device).
+Desktop is 3440 x 1440 @ 50 Hz
+Invalid initial resolution 84 x 84 - forcing to 100 x 100
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /home/alex/Projects/ml-agents/training-envs-executables/linux/SnowballTarget/SnowballTarget_Data/UnitySubsystems
+GfxDevice: creating device client; threaded=1; jobified=1
+Renderer: RENOIR (renoir, LLVM 15.0.7, DRM 3.47, 5.19.0-42-generic)
+Vendor: AMD
+Version: 4.6 (Core Profile) Mesa 22.2.5
+GLES: 0
+ GL_AMD_conservative_depth GL_AMD_depth_clamp_separate GL_AMD_draw_buffers_blend GL_AMD_framebuffer_multisample_advanced GL_AMD_gpu_shader_int64 GL_AMD_multi_draw_indirect GL_AMD_performance_monitor 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_bindless_texture GL_ARB_blend_func_extended GL_ARB_buffer_storage GL_ARB_clear_buffer_object GL_ARB_clear_texture GL_ARB_clip_control GL_ARB_color_buffer_float 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_copy_image GL_ARB_cull_dist
+ance 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_ARB_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_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_sparse_buffer GL_ARB_sparse_texture GL_ARB_sparse_texture2 GL_ARB_sparse_texture_clamp GL_ARB_spirv_extensio
+ns GL_ARB_stencil_texturing GL_ARB_sync GL_ARB_tessellation_shader GL_ARB_texture_barrier 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_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_ATI_blend_equation_separate GL_ATI_meminfo GL_ATI_texture_float GL_ATI_texture_mirror_once GL_EXT_EGL_image_storage GL_EXT_EGL_sync GL_EXT_abgr GL_EXT_blend_equation_separate GL_EXT_demote_to_helper_invocation 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_semaphore GL_EXT_semaphore_fd GL_EXT_shader_image_load_formatted GL_EXT_shader_image_load_store GL_EXT_shader_integer_mix GL_EXT_shader_samples_identical 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_text
+ure_integer GL_EXT_texture_mirror_clamp GL_EXT_texture_sRGB GL_EXT_texture_sRGB_R8 GL_EXT_texture_sRGB_decode GL_EXT_texture_shadow_lod GL_EXT_texture_shared_exponent GL_EXT_texture_snorm GL_EXT_texture_swizzle GL_EXT_timer_query GL_EXT_transform_feedback GL_EXT_vertex_array_bgra GL_EXT_vertex_attrib_64bit GL_EXT_window_rectangles GL_IBM_multimode_draw_arrays GL_INTEL_blackhole_render GL_KHR_blend_equation_advanced 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_compute_shader_derivatives GL_NV_conditional_render GL_NV_copy_image GL_NV_depth_clamp GL_NV_packed_depth_stencil GL_NV_shader_atomic_int64 GL_NV_texture_barrier GL_NV_vdpau_interop GL_OES_EGL_image GL_S3_s
+3tc
+OPENGL LOG: Creating OpenGL 4.6 graphics device ; Context level <OpenGL 4.5> ; Context handle 31851584
+Begin MonoManager ReloadAssembly
+- Completed reload, in 0.065 seconds
+Default vsync count 1
+requesting resize 84 x 84
+resizing window to 84 x 84
+Desktop is 3440 x 1440 @ 50 Hz
+UnloadTime: 0.902489 ms
+requesting resize 84 x 84
+resizing window to 84 x 84
+Desktop is 3440 x 1440 @ 50 Hz
+Setting up 8 worker threads for Enlighten.
+Memory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+ StackAllocators : 
+ [ALLOC_TEMP_MAIN]
+ Peak usage frame count: [8.0 KB-16.0 KB]: 5369 frames, [16.0 KB-32.0 KB]: 91 frames, [2.0 MB-4.0 MB]: 1 frames
+ Initial Block Size 4.0 MB
+ Current Block Size 4.0 MB
+ Peak Allocated Bytes 2.0 MB
+ Overflow Count 0
+ [ALLOC_TEMP_Loading.AsyncRead]
+ Initial Block Size 64.0 KB
+ Current Block Size 64.0 KB
+ Peak Allocated Bytes 220 B
+ Overflow Count 0
+ [ALLOC_TEMP_Loading.PreloadManager]
+ Initial Block Size 256.0 KB
+ Current Block Size 304.0 KB
+ Peak Allocated Bytes 228.9 KB
+ Overflow Count 4
+ [ALLOC_TEMP_Background Job.Worker 8]
+ Initial Block Size 32.0 KB
+ Current Block Size 32.0 KB
+ Peak Allocated Bytes 0 B
+ Overflow Count 0
+ [ALLOC_TEMP_Job.Worker 6]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 6.8 KB
+ Overflow Count 0
+ [ALLOC_TEMP_Job.Worker 0]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 6.8 KB
+ Overflow Count 0
+ [ALLOC_TEMP_Background Job.Worker 10]
+ Initial Block Size 32.0 KB
+ Current Block Size 32.0 KB
+ Peak Allocated Bytes 0 B
+ Overflow Count 0
+ [ALLOC_TEMP_Background Job.Worker 9]
+ Initial Block Size 32.0 KB
+ Current Block Size 32.0 KB
+ Peak Allocated Bytes 0 B
+ Overflow Count 0
+ [ALLOC_TEMP_Job.Worker 5]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 6.8 KB
+ Overflow Count 0
+ [ALLOC_TEMP_Background Job.Worker 14]
+ Initial Block Size 32.0 KB
+ Current Block Size 32.0 KB
+ Peak Allocated Bytes 0 B
+ Overflow Count 0
+ [ALLOC_TEMP_Background Job.Worker 6]
+ Initial Block Size 32.0 KB
+ Current Block Size 32.0 KB
+ Peak Allocated Bytes 0 B
+ Overflow Count 0
+ [ALLOC_TEMP_Job.Worker 4]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 20.3 KB
+ Overflow Count 0
+ [ALLOC_TEMP_Job.Worker 14]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 6.8 KB
+ Overflow Count 0
+ [ALLOC_TEMP_Job.Worker 3]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 6.8 KB
+ Overflow Count 0
+ [ALLOC_TEMP_Job.Worker 13]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 6.8 KB
+ Overflow Count 0
+ [ALLOC_TEMP_Background Job.Worker 12]
+ Initial Block Size 32.0 KB
+ Current Block Size 32.0 KB
+ Peak Allocated Bytes 0 B
+ Overflow Count 0
+ [ALLOC_TEMP_EnlightenWorker] x 8
+ Initial Block Size 64.0 KB
+ Current Block Size 64.0 KB
+ Peak Allocated Bytes 0 B
+ Overflow Count 0
+ [ALLOC_TEMP_Background Job.Worker 15]
+ Initial Block Size 32.0 KB
+ Current Block Size 32.0 KB
+ Peak Allocated Bytes 0 B
+ Overflow Count 0
+ [ALLOC_TEMP_Background Job.Worker 1]
+ Initial Block Size 32.0 KB
+ Current Block Size 32.0 KB
+ Peak Allocated Bytes 0 B
+ Overflow Count 0
+ [ALLOC_TEMP_Background Job.Worker 2]
+ Initial Block Size 32.0 KB
+ Current Block Size 32.0 KB
+ Peak Allocated Bytes 0 B
+ Overflow Count 0
+ [ALLOC_TEMP_Background Job.Worker 7]
+ Initial Block Size 32.0 KB
+ Current Block Size 32.0 KB
+ Peak Allocated Bytes 0 B
+ Overflow Count 0
+ [ALLOC_TEMP_UnityGfxDeviceWorker]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 45.6 KB
+ Overflow Count 0
+ [ALLOC_TEMP_AssetGarbageCollectorHelper] x 15
+ 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_Job.Worker 9]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 6.8 KB
+ 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 8]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 6.8 KB
+ Overflow Count 0
+ [ALLOC_TEMP_Job.Worker 7]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 6.8 KB
+ Overflow Count 0
+ [ALLOC_TEMP_Job.Worker 1]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 6.8 KB
+ Overflow Count 0
+ [ALLOC_TEMP_Job.Worker 2]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 6.8 KB
+ Overflow Count 0
+ [ALLOC_TEMP_Background Job.Worker 3]
+ Initial Block Size 32.0 KB
+ Current Block Size 32.0 KB
+ Peak Allocated Bytes 0 B
+ Overflow Count 0
+ [ALLOC_TEMP_Background Job.Worker 11]
+ Initial Block Size 32.0 KB
+ Current Block Size 32.0 KB
+ Peak Allocated Bytes 0 B
+ Overflow Count 0
+ [ALLOC_TEMP_Job.Worker 10]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 6.8 KB
+ Overflow Count 0
+ [ALLOC_TEMP_Background Job.Worker 0]
+ Initial Block Size 32.0 KB
+ Current Block Size 32.0 KB
+ Peak Allocated Bytes 0 B
+ Overflow Count 0
+ [ALLOC_TEMP_Job.Worker 11]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 6.8 KB
+ Overflow Count 0
+ [ALLOC_TEMP_Job.Worker 12]
+ Initial Block Size 256.0 KB
+ Current Block Size 256.0 KB
+ Peak Allocated Bytes 6.8 KB
+ Overflow Count 0
+ [ALLOC_TEMP_Background Job.Worker 4]
+ Initial Block Size 32.0 KB
+ Current Block Size 32.0 KB
+ Peak Allocated Bytes 0 B
+ Overflow Count 0
+ [ALLOC_TEMP_BatchDeleteObjects]
+ Initial Block Size 64.0 KB
+ Current Block Size 64.0 KB
+ Peak Allocated Bytes 0 B
+ Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+ Peak main deferred allocation count 40
+ [ALLOC_BUCKET]
+ Large Block size 4.0 MB
+ Used Block count 1
+ Peak Allocated bytes 1.8 MB
+ [ALLOC_DEFAULT_MAIN]
+ Peak usage frame count: [8.0 MB-16.0 MB]: 5461 frames
+ Requested Block Size 16.0 MB
+ Peak Block count 2
+ Peak Allocated memory 15.6 MB
+ Peak Large allocation bytes 0 B
+ [ALLOC_DEFAULT_THREAD]
+ Peak usage frame count: [16.0 MB-32.0 MB]: 5461 frames
+ Requested Block Size 16.0 MB
+ Peak Block count 1
+ Peak Allocated memory 26.3 MB
+ Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+ Initial Block Size 2.0 MB
+ Used Block Count 1
+ Overflow Count (too large) 0
+ Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+ Initial Block Size 2.0 MB
+ Used Block Count 1
+ Overflow Count (too large) 0
+ Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+ Initial Block Size 2.0 MB
+ Used Block Count 2
+ Overflow Count (too large) 0
+ Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+ Initial Block Size 1.0 MB
+ Used Block Count 3
+ Overflow Count (too large) 0
+ Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+ Peak main deferred allocation count 1
+ [ALLOC_BUCKET]
+ Large Block size 4.0 MB
+ Used Block count 1
+ Peak Allocated bytes 1.8 MB
+ [ALLOC_GFX_MAIN]
+ Peak usage frame count: [32.0 KB-64.0 KB]: 512 frames, [64.0 KB-128.0 KB]: 4948 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: [0.5 MB-1.0 MB]: 5461 frames
+ Requested Block Size 16.0 MB
+ Peak Block count 1
+ Peak Allocated memory 0.9 MB
+ Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+ Peak main deferred allocation count 4
+ [ALLOC_BUCKET]
+ Large Block size 4.0 MB
+ Used Block count 1
+ Peak Allocated bytes 1.8 MB
+ [ALLOC_CACHEOBJECTS_MAIN]
+ Peak usage frame count: [1.0 MB-2.0 MB]: 5461 frames
+ Requested Block Size 4.0 MB
+ Peak Block count 1
+ Peak Allocated memory 1.2 MB
+ Peak Large allocation bytes 0 B
+ [ALLOC_CACHEOBJECTS_THREAD]
+ Peak usage frame count: [2.0 MB-4.0 MB]: 5460 frames, [4.0 MB-8.0 MB]: 1 frames
+ Requested Block Size 4.0 MB
+ Peak Block count 2
+ Peak Allocated memory 5.1 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 1.8 MB
+ [ALLOC_TYPETREE_MAIN]
+ Peak usage frame count: [0-1.0 KB]: 5461 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]: 5461 frames
+ Requested Block Size 2.0 MB
+ Peak Block count 1
+ Peak Allocated memory 1.7 KB
+ Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -0,0 +1,377 @@
+{
+ "name": "root",
+ "gauges": {
+ "SnowballTarget.Policy.Entropy.mean": {
+ "value": 0.9347748756408691,
+ "min": 0.9347748756408691,
+ "max": 2.870821237564087,
+ "count": 20
+ },
+ "SnowballTarget.Policy.Entropy.sum": {
+ "value": 8925.23046875,
+ "min": 8925.23046875,
+ "max": 29431.658203125,
+ "count": 20
+ },
+ "SnowballTarget.Step.mean": {
+ "value": 199984.0,
+ "min": 9952.0,
+ "max": 199984.0,
+ "count": 20
+ },
+ "SnowballTarget.Step.sum": {
+ "value": 199984.0,
+ "min": 9952.0,
+ "max": 199984.0,
+ "count": 20
+ },
+ "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+ "value": 13.051813125610352,
+ "min": 0.40046122670173645,
+ "max": 13.051813125610352,
+ "count": 20
+ },
+ "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+ "value": 2545.103515625,
+ "min": 77.6894760131836,
+ "max": 2626.13916015625,
+ "count": 20
+ },
+ "SnowballTarget.Environment.EpisodeLength.mean": {
+ "value": 199.0,
+ "min": 199.0,
+ "max": 199.0,
+ "count": 20
+ },
+ "SnowballTarget.Environment.EpisodeLength.sum": {
+ "value": 8756.0,
+ "min": 8756.0,
+ "max": 10945.0,
+ "count": 20
+ },
+ "SnowballTarget.Losses.PolicyLoss.mean": {
+ "value": 0.06582016309988045,
+ "min": 0.06301620793180751,
+ "max": 0.07173947486632695,
+ "count": 20
+ },
+ "SnowballTarget.Losses.PolicyLoss.sum": {
+ "value": 0.2632806523995218,
+ "min": 0.25206483172723004,
+ "max": 0.3586973743316348,
+ "count": 20
+ },
+ "SnowballTarget.Losses.ValueLoss.mean": {
+ "value": 0.1848845719268509,
+ "min": 0.13145641689006166,
+ "max": 0.2922152230552598,
+ "count": 20
+ },
+ "SnowballTarget.Losses.ValueLoss.sum": {
+ "value": 0.7395382877074036,
+ "min": 0.5258256675602466,
+ "max": 1.4610761152762992,
+ "count": 20
+ },
+ "SnowballTarget.Policy.LearningRate.mean": {
+ "value": 8.082097306000005e-06,
+ "min": 8.082097306000005e-06,
+ "max": 0.000291882002706,
+ "count": 20
+ },
+ "SnowballTarget.Policy.LearningRate.sum": {
+ "value": 3.232838922400002e-05,
+ "min": 3.232838922400002e-05,
+ "max": 0.00138516003828,
+ "count": 20
+ },
+ "SnowballTarget.Policy.Epsilon.mean": {
+ "value": 0.10269400000000001,
+ "min": 0.10269400000000001,
+ "max": 0.19729400000000002,
+ "count": 20
+ },
+ "SnowballTarget.Policy.Epsilon.sum": {
+ "value": 0.41077600000000003,
+ "min": 0.41077600000000003,
+ "max": 0.96172,
+ "count": 20
+ },
+ "SnowballTarget.Policy.Beta.mean": {
+ "value": 0.0001444306000000001,
+ "min": 0.0001444306000000001,
+ "max": 0.0048649706,
+ "count": 20
+ },
+ "SnowballTarget.Policy.Beta.sum": {
+ "value": 0.0005777224000000004,
+ "min": 0.0005777224000000004,
+ "max": 0.023089828,
+ "count": 20
+ },
+ "SnowballTarget.Environment.CumulativeReward.mean": {
+ "value": 26.386363636363637,
+ "min": 3.2954545454545454,
+ "max": 26.386363636363637,
+ "count": 20
+ },
+ "SnowballTarget.Environment.CumulativeReward.sum": {
+ "value": 1161.0,
+ "min": 145.0,
+ "max": 1410.0,
+ "count": 20
+ },
+ "SnowballTarget.Policy.ExtrinsicReward.mean": {
+ "value": 26.386363636363637,
+ "min": 3.2954545454545454,
+ "max": 26.386363636363637,
+ "count": 20
+ },
+ "SnowballTarget.Policy.ExtrinsicReward.sum": {
+ "value": 1161.0,
+ "min": 145.0,
+ "max": 1410.0,
+ "count": 20
+ },
+ "SnowballTarget.IsTraining.mean": {
+ "value": 1.0,
+ "min": 1.0,
+ "max": 1.0,
+ "count": 20
+ },
+ "SnowballTarget.IsTraining.sum": {
+ "value": 1.0,
+ "min": 1.0,
+ "max": 1.0,
+ "count": 20
+ }
+ },
+ "metadata": {
+ "timer_format_version": "0.1.0",
+ "start_time_seconds": "1684854693",
+ "python_version": "3.10.6 (main, Mar 10 2023, 10:55:28) [GCC 11.3.0]",
+ "command_line_arguments": "/home/alex/.local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget",
+ "mlagents_version": "0.31.0.dev0",
+ "mlagents_envs_version": "0.31.0.dev0",
+ "communication_protocol_version": "1.5.0",
+ "pytorch_version": "1.11.0+cu113",
+ "numpy_version": "1.21.2",
+ "end_time_seconds": "1684854911"
+ },
+ "total": 217.974715048,
+ "count": 1,
+ "self": 0.31908150799995383,
+ "children": {
+ "run_training.setup": {
+ "total": 0.009028280000052291,
+ "count": 1,
+ "self": 0.009028280000052291
+ },
+ "TrainerController.start_learning": {
+ "total": 217.64660526,
+ "count": 1,
+ "self": 0.35975305700105764,
+ "children": {
+ "TrainerController._reset_env": {
+ "total": 5.921296913999981,
+ "count": 1,
+ "self": 5.921296913999981
+ },
+ "TrainerController.advance": {
+ "total": 211.29437028099903,
+ "count": 18203,
+ "self": 0.19730869699412779,
+ "children": {
+ "env_step": {
+ "total": 211.0970615840049,
+ "count": 18203,
+ "self": 144.734286379016,
+ "children": {
+ "SubprocessEnvManager._take_step": {
+ "total": 66.16749756399395,
+ "count": 18203,
+ "self": 0.969686294990538,
+ "children": {
+ "TorchPolicy.evaluate": {
+ "total": 65.19781126900341,
+ "count": 18203,
+ "self": 65.19781126900341
+ }
+ }
+ },
+ "workers": {
+ "total": 0.19527764099495926,
+ "count": 18203,
+ "self": 0.0,
+ "children": {
+ "worker_root": {
+ "total": 217.23435935799557,
+ "count": 18203,
+ "is_parallel": true,
+ "self": 114.45250543799409,
+ "children": {
+ "run_training.setup": {
+ "total": 0.0,
+ "count": 0,
+ "is_parallel": true,
+ "self": 0.0,
+ "children": {
+ "steps_from_proto": {
+ "total": 0.0009598080000614573,
+ "count": 1,
+ "is_parallel": true,
+ "self": 0.00024892700002965285,
+ "children": {
+ "_process_rank_one_or_two_observation": {
+ "total": 0.0007108810000318044,
+ "count": 10,
+ "is_parallel": true,
+ "self": 0.0007108810000318044
+ }
+ }
+ },
+ "UnityEnvironment.step": {
+ "total": 0.0214716950000593,
+ "count": 1,
+ "is_parallel": true,
+ "self": 0.00022902200009866647,
+ "children": {
+ "UnityEnvironment._generate_step_input": {
+ "total": 0.00019200299993826775,
+ "count": 1,
+ "is_parallel": true,
+ "self": 0.00019200299993826775
+ },
+ "communicator.exchange": {
+ "total": 0.020242983999992248,
+ "count": 1,
+ "is_parallel": true,
+ "self": 0.020242983999992248
+ },
+ "steps_from_proto": {
+ "total": 0.0008076860000301167,
+ "count": 1,
+ "is_parallel": true,
+ "self": 0.0001799890000029336,
+ "children": {
+ "_process_rank_one_or_two_observation": {
+ "total": 0.0006276970000271831,
+ "count": 10,
+ "is_parallel": true,
+ "self": 0.0006276970000271831
+ }
+ }
+ }
+ }
+ }
+ }
+ },
+ "UnityEnvironment.step": {
+ "total": 102.78185392000148,
+ "count": 18202,
+ "is_parallel": true,
+ "self": 4.49393466698416,
+ "children": {
+ "UnityEnvironment._generate_step_input": {
+ "total": 2.549921165006367,
+ "count": 18202,
+ "is_parallel": true,
+ "self": 2.549921165006367
+ },
+ "communicator.exchange": {
+ "total": 81.53672325901357,
+ "count": 18202,
+ "is_parallel": true,
+ "self": 81.53672325901357
+ },
+ "steps_from_proto": {
+ "total": 14.201274828997384,
+ "count": 18202,
+ "is_parallel": true,
+ "self": 3.0012425939977447,
+ "children": {
+ "_process_rank_one_or_two_observation": {
+ "total": 11.20003223499964,
+ "count": 182020,
+ "is_parallel": true,
+ "self": 11.20003223499964
+ }
+ }
+ }
+ }
+ }
+ }
+ }
+ }
+ }
+ }
+ }
+ }
+ },
+ "trainer_threads": {
+ "total": 4.7773999995115446e-05,
+ "count": 1,
+ "self": 4.7773999995115446e-05,
+ "children": {
+ "thread_root": {
+ "total": 0.0,
+ "count": 0,
+ "is_parallel": true,
+ "self": 0.0,
+ "children": {
+ "trainer_advance": {
+ "total": 210.7673682289685,
+ "count": 186339,
+ "is_parallel": true,
+ "self": 1.9597381369794675,
+ "children": {
+ "process_trajectory": {
+ "total": 109.65982094098888,
+ "count": 186339,
+ "is_parallel": true,
+ "self": 109.25140383498899,
+ "children": {
+ "RLTrainer._checkpoint": {
+ "total": 0.408417105999888,
+ "count": 4,
+ "is_parallel": true,
+ "self": 0.408417105999888
+ }
+ }
+ },
+ "_update_policy": {
+ "total": 99.14780915100016,
+ "count": 90,
+ "is_parallel": true,
+ "self": 27.888865099996337,
+ "children": {
+ "TorchPPOOptimizer.update": {
+ "total": 71.25894405100382,
+ "count": 4587,
+ "is_parallel": true,
+ "self": 71.25894405100382
+ }
+ }
+ }
+ }
+ }
+ }
+ }
+ }
+ },
+ "TrainerController._save_models": {
+ "total": 0.07113723399993432,
+ "count": 1,
+ "self": 0.0005538009999099813,
+ "children": {
+ "RLTrainer._checkpoint": {
+ "total": 0.07058343300002434,
+ "count": 1,
+ "self": 0.07058343300002434
+ }
+ }
+ }
+ }
+ }
+ }
+}

run_logs/training_status.json

@@ -0,0 +1,65 @@
+{
+ "SnowballTarget": {
+ "checkpoints": [
+ {
+ "steps": 49936,
+ "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-49936.onnx",
+ "reward": 13.181818181818182,
+ "creation_time": 1684854751.4693744,
+ "auxillary_file_paths": [
+ "results/SnowballTarget/SnowballTarget/SnowballTarget-49936.pt"
+ ]
+ },
+ {
+ "steps": 99960,
+ "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-99960.onnx",
+ "reward": 21.0,
+ "creation_time": 1684854803.9547987,
+ "auxillary_file_paths": [
+ "results/SnowballTarget/SnowballTarget/SnowballTarget-99960.pt"
+ ]
+ },
+ {
+ "steps": 149984,
+ "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-149984.onnx",
+ "reward": 26.181818181818183,
+ "creation_time": 1684854857.9216542,
+ "auxillary_file_paths": [
+ "results/SnowballTarget/SnowballTarget/SnowballTarget-149984.pt"
+ ]
+ },
+ {
+ "steps": 199984,
+ "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-199984.onnx",
+ "reward": 26.272727272727273,
+ "creation_time": 1684854910.9978426,
+ "auxillary_file_paths": [
+ "results/SnowballTarget/SnowballTarget/SnowballTarget-199984.pt"
+ ]
+ },
+ {
+ "steps": 200112,
+ "file_path": "results/SnowballTarget/SnowballTarget/SnowballTarget-200112.onnx",
+ "reward": 26.272727272727273,
+ "creation_time": 1684854911.0842972,
+ "auxillary_file_paths": [
+ "results/SnowballTarget/SnowballTarget/SnowballTarget-200112.pt"
+ ]
+ }
+ ],
+ "final_checkpoint": {
+ "steps": 200112,
+ "file_path": "results/SnowballTarget/SnowballTarget.onnx",
+ "reward": 26.272727272727273,
+ "creation_time": 1684854911.0842972,
+ "auxillary_file_paths": [
+ "results/SnowballTarget/SnowballTarget/SnowballTarget-200112.pt"
+ ]
+ }
+ },
+ "metadata": {
+ "stats_format_version": "0.3.0",
+ "mlagents_version": "0.31.0.dev0",
+ "torch_version": "1.11.0+cu113"
+ }
+}