Push trained model

README.md

@@ -0,0 +1,35 @@
+---
+library_name: ml-agents
+tags:
+- SoccerTwos
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-SoccerTwos
+---
+
+  # **poca** Agent playing **SoccerTwos**
+  This is a trained model of a **poca** agent playing **SoccerTwos**
+  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: Pyro-X2/SoccerTwos-ML-Agents
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

SoccerTwos.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37836ecca446b3ff172b282e84eb16aec6dc0058a895833050e7064b7cb80de7
+size 1768747

SoccerTwos/SoccerTwos-1499951.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56bfa6f38d84d850f5bcadd1efec344d2b53b197e96e8fdacd640710fc7083d7
+size 1768747

SoccerTwos/SoccerTwos-1499951.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e432b2f44f7bab9d9dd6e66699d8e3ce332a42c8c66827e2ab08773ab68a2470
+size 28432022

SoccerTwos/SoccerTwos-19904.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16595e8e9f680fd58d884705f59579345554c8870442af212b8dd914aae2cdc0
+size 1156862

SoccerTwos/SoccerTwos-19904.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78ff7cea9e4a535095bb95443fbd949a5c249534b899b139ef0e9b35fa38a85e
+size 6884859

SoccerTwos/SoccerTwos-1999946.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7879ae50719481c39fc647026bcf5467bcb04f8c96074892d437f90881b32819
+size 1768747

SoccerTwos/SoccerTwos-1999946.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f715e2525e1cfd4508287906ae177d2ea7bf7b860ceaed3f287f186e5c2aa1d
+size 28432022

SoccerTwos/SoccerTwos-321838.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37836ecca446b3ff172b282e84eb16aec6dc0058a895833050e7064b7cb80de7
+size 1768747

SoccerTwos/SoccerTwos-321838.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b4fa7a502e428d894139997bf78c401d847e381cf3854ce5c9db8117ed6bf4d
+size 28431898

SoccerTwos/SoccerTwos-499674.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4a49f6b188db214dc9fbad9d9d2a639dda26e00406ab7449ad87465505a8967
+size 1768747

SoccerTwos/SoccerTwos-499674.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c0d736895f9714af3c9f853e1e49def614579b14cde0ab617cad9b2634f28ea
+size 28431898

SoccerTwos/SoccerTwos-999908.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81b35c8853447e915998f80fd72a964876ed6d32dac3030458e07fdbddc700c6
+size 1768747

SoccerTwos/SoccerTwos-999908.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:734650d1d03f78bd93fc4e27eab64d4c3c7da79dc4824a4ec6cbeff6a308d99f
+size 28431898

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e888c3001031678e7770063cdb9cd146ea0ee00d2d983a376bae46669a9c046
+size 28431030

SoccerTwos/events.out.tfevents.1735587776.jakub.9396.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be27403b71febfe31620a73557539b03eedde8ca662fd7d26cc4b51f9b99bede
+size 2380733

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "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}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 5000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "/home/jakub/machine_learning/rl/unity/hugging_face_rl_course/training-envs-executables/linux/SoccerTwos.x86_64", "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": "Soccer", "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 +1,84 @@
+default_settings: null
+behaviors:
+  SoccerTwos:
+    trainer_type: poca
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: constant
+      beta_schedule: constant
+      epsilon_schedule: constant
+    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
+    init_path: null
+    keep_checkpoints: 5
+    even_checkpoints: false
+    max_steps: 5000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 50000
+      team_change: 200000
+      swap_steps: 2000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: /home/jakub/machine_learning/rl/unity/hugging_face_rl_course/training-envs-executables/linux/SoccerTwos.x86_64
+  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: Soccer
+  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 +1,284 @@
+Mono path[0] = '/home/jakub/machine_learning/rl/unity/hugging_face_rl_course/training-envs-executables/linux/SoccerTwos_Data/Managed'
+Mono config path = '/home/jakub/machine_learning/rl/unity/hugging_face_rl_course/training-envs-executables/linux/SoccerTwos_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+Display 0 '0': 2560x1600 (primary device).
+Desktop is 2560 x 1600 @ 165 Hz
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /home/jakub/machine_learning/rl/unity/hugging_face_rl_course/training-envs-executables/linux/SoccerTwos_Data/UnitySubsystems
+GfxDevice: creating device client; threaded=1; jobified=0
+Renderer: Mesa Intel(R) Graphics (ADL GT2)
+Vendor:   Intel
+Version:  4.6 (Core Profile) Mesa 23.2.1-1ubuntu3.1~22.04.2
+GLES:     0
+ GL_3DFX_texture_compression_FXT1 GL_AMD_conservative_depth GL_AMD_depth_clamp_separate GL_AMD_draw_buffers_blend 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_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_compute_variable_group_size 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_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_fragment_shader_interlock 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_po
+int_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 G
+L_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_viewpor
+t_array GL_ATI_blend_equation_separate GL_ATI_texture_float GL_EXT_EGL_image_storage GL_EXT_EGL_sync GL_EXT_abgr GL_EXT_blend_equation_separate GL_EXT_debug_label GL_EXT_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_framebuffer_fetch GL_EXT_shader_framebuffer_fetch_non_coherent 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_texture_integer 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_IBM_multimode_draw_arrays GL_INTEL_blackhole_render GL_INTEL_conservative_rasterization GL_INTEL_performance_query GL_INTEL_shader_atomic_float_minmax GL_INTEL_shader_integer_functions2 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_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_fragment_shader_interlock GL_NV_packed_depth_stencil GL_NV_texture_barrier GL_OES_EGL_image GL_S3_s3tc
+OPENGL LOG: Creating OpenGL 4.6 graphics device ; Context level  <OpenGL 4.5> ; Context handle 13345712
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.044 seconds
+Default vsync count 1
+requesting resize 1261 x 931
+resizing window to 1261 x 931
+Desktop is 2560 x 1600 @ 165 Hz
+UnloadTime: 1.943898 ms
+Registered Communicator in Agent.
+Setting up 10 worker threads for Enlighten.
+requesting resize 84 x 84
+resizing window to 84 x 84
+Desktop is 2560 x 1600 @ 165 Hz
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+X connection to :1 broken (explicit kill or server shutdown).

run_logs/timers.json

@@ -0,0 +1,417 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 3.2327919006347656,
+            "min": 3.216299057006836,
+            "max": 3.2957403659820557,
+            "count": 32
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 16138.09765625,
+            "min": 16138.09765625,
+            "max": 105463.65625,
+            "count": 32
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 852.3333333333334,
+            "min": 571.375,
+            "max": 999.0,
+            "count": 32
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 20456.0,
+            "min": 14552.0,
+            "max": 27884.0,
+            "count": 32
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1205.3368658228078,
+            "min": 1197.9700391146837,
+            "max": 1205.3368658228078,
+            "count": 28
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 4821.347463291231,
+            "min": 2401.4871306689274,
+            "max": 9639.75817790043,
+            "count": 28
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 319838.0,
+            "min": 9176.0,
+            "max": 319838.0,
+            "count": 32
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 319838.0,
+            "min": 9176.0,
+            "max": 319838.0,
+            "count": 32
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.004035059828311205,
+            "min": -0.037238236516714096,
+            "max": -0.0008190153748728335,
+            "count": 32
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -0.04842071980237961,
+            "min": -0.44685885310173035,
+            "max": -0.009828184731304646,
+            "count": 32
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.0034829166252166033,
+            "min": -0.03728574514389038,
+            "max": -0.001886433339677751,
+            "count": 32
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -0.041795000433921814,
+            "min": -0.44742894172668457,
+            "max": -0.022637199610471725,
+            "count": 32
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 32
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 32
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.06640000144640605,
+            "min": -0.4,
+            "max": 0.19061538806328407,
+            "count": 32
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -0.7968000173568726,
+            "min": -6.0,
+            "max": 2.478000044822693,
+            "count": 32
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.06640000144640605,
+            "min": -0.4,
+            "max": 0.19061538806328407,
+            "count": 32
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -0.7968000173568726,
+            "min": -6.0,
+            "max": 2.478000044822693,
+            "count": 32
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 32
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 32
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.016676541194707777,
+            "min": 0.013907801132882014,
+            "max": 0.020427747846891484,
+            "count": 14
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.016676541194707777,
+            "min": 0.013907801132882014,
+            "max": 0.020427747846891484,
+            "count": 14
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.003029419241162638,
+            "min": 0.0006140647717984393,
+            "max": 0.003925894301695128,
+            "count": 14
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.003029419241162638,
+            "min": 0.0006140647717984393,
+            "max": 0.003925894301695128,
+            "count": 14
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.0030393395689316096,
+            "min": 0.0006003286990259464,
+            "max": 0.004084089452711244,
+            "count": 14
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.0030393395689316096,
+            "min": 0.0006003286990259464,
+            "max": 0.004084089452711244,
+            "count": 14
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 14
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 14
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000004,
+            "max": 0.20000000000000007,
+            "count": 14
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000004,
+            "max": 0.20000000000000007,
+            "count": 14
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 14
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 14
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1735587242",
+        "python_version": "3.10.12 (main, Nov  6 2024, 20:22:13) [GCC 11.4.0]",
+        "command_line_arguments": "/home/jakub/.local/bin/mlagents-learn ../hugging_face_rl_course/soccer_config.yaml --env=/home/jakub/machine_learning/rl/unity/hugging_face_rl_course/training-envs-executables/linux/SoccerTwos.x86_64 --run-id=Soccer --force",
+        "mlagents_version": "1.1.0",
+        "mlagents_envs_version": "1.1.0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.4.0+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1735587541"
+    },
+    "total": 298.844128273,
+    "count": 1,
+    "self": 0.10385578600016743,
+    "children": {
+        "run_training.setup": {
+            "total": 0.013472136000018509,
+            "count": 1,
+            "self": 0.013472136000018509
+        },
+        "TrainerController.start_learning": {
+            "total": 298.72680035099984,
+            "count": 1,
+            "self": 0.30513061800684227,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 3.494470645000547,
+                    "count": 2,
+                    "self": 3.494470645000547
+                },
+                "TrainerController.advance": {
+                    "total": 294.8135898799924,
+                    "count": 20868,
+                    "self": 0.3121210679996693,
+                    "children": {
+                        "env_step": {
+                            "total": 237.34066501700227,
+                            "count": 20868,
+                            "self": 170.22443586809686,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 66.9262380699497,
+                                    "count": 20868,
+                                    "self": 1.8119505199210835,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 65.11428755002862,
+                                            "count": 41474,
+                                            "self": 65.11428755002862
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.18999107895569978,
+                                    "count": 20868,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 298.25997424494653,
+                                            "count": 20868,
+                                            "is_parallel": true,
+                                            "self": 161.68482900892604,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0020667039998443215,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005585399994743057,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0015081640003700159,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0015081640003700159
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.017134272000021156,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00033839199977592216,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0002395940000496921,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0002395940000496921
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.015621185999862064,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.015621185999862064
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0009351000003334775,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00019818800001303316,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0007369120003204443,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0007369120003204443
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 136.5740734050205,
+                                                    "count": 20867,
+                                                    "is_parallel": true,
+                                                    "self": 7.508408150035848,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 4.357261193983504,
+                                                            "count": 20867,
+                                                            "is_parallel": true,
+                                                            "self": 4.357261193983504
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 103.90321406499424,
+                                                            "count": 20867,
+                                                            "is_parallel": true,
+                                                            "self": 103.90321406499424
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 20.805189996006902,
+                                                            "count": 41734,
+                                                            "is_parallel": true,
+                                                            "self": 3.943119694034067,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 16.862070301972835,
+                                                                    "count": 166936,
+                                                                    "is_parallel": true,
+                                                                    "self": 16.862070301972835
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.0010718309999901976,
+                                                    "count": 2,
+                                                    "is_parallel": true,
+                                                    "self": 0.00021750999985670205,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.0008543210001334955,
+                                                            "count": 8,
+                                                            "is_parallel": true,
+                                                            "self": 0.0008543210001334955
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 57.16080379499044,
+                            "count": 20867,
+                            "self": 2.1533794310212215,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 14.373591061969819,
+                                    "count": 20867,
+                                    "self": 14.373591061969819
+                                },
+                                "_update_policy": {
+                                    "total": 40.6338333019994,
+                                    "count": 14,
+                                    "self": 18.461123868998584,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 22.17270943300082,
+                                            "count": 429,
+                                            "self": 22.17270943300082
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 6.790000952605624e-07,
+                    "count": 1,
+                    "self": 6.790000952605624e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.11360852899997553,
+                    "count": 1,
+                    "self": 0.0009228669996446115,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.11268566200033092,
+                            "count": 1,
+                            "self": 0.11268566200033092
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,30 @@
+{
+    "SoccerTwos": {
+        "elo": 1205.948218641586,
+        "checkpoints": [
+            {
+                "steps": 321838,
+                "file_path": "results/Soccer/SoccerTwos/SoccerTwos-321838.onnx",
+                "reward": 0.0,
+                "creation_time": 1735587541.6493616,
+                "auxillary_file_paths": [
+                    "results/Soccer/SoccerTwos/SoccerTwos-321838.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 321838,
+            "file_path": "results/Soccer/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1735587541.6493616,
+            "auxillary_file_paths": [
+                "results/Soccer/SoccerTwos/SoccerTwos-321838.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0",
+        "torch_version": "2.4.0+cu121"
+    }
+}