First Push

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: N0de/poca-SoccerTwos
+  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 sha256:082eefbcf30c4e5a3df40e788ab2a2d93655edfb4507345438a9f3d43fc5e0a5
+size 1768747

SoccerTwos/SoccerTwos-1499002.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c87ed9cdf1ca560cb982dc7af83cf3ee499255d7d8909a6337da1fa1d3400d1
+size 1768747

SoccerTwos/SoccerTwos-1499002.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a2ca8b6eba47bb2061f8c15f9bba92ff5771b0d8468a0b432ac616fe32f4b38
+size 28432022

SoccerTwos/SoccerTwos-1999652.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:390f0d2a69ee5a2a5ec3e05eeb6bac104827a5134f9bef3e4c790e2b88cdd071
+size 1768747

SoccerTwos/SoccerTwos-1999652.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac1303fbcf15c5b4b4a6012909cbbcc84742c3367a0e00b7fec77ab37e048673
+size 28432022

SoccerTwos/SoccerTwos-43014.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:082eefbcf30c4e5a3df40e788ab2a2d93655edfb4507345438a9f3d43fc5e0a5
+size 1768747

SoccerTwos/SoccerTwos-43014.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a873da96bf0b8277421c9fff8b35412f873421d4b7377ccba9e60985ff383bd3
+size 28430110

SoccerTwos/SoccerTwos-499728.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1d5ab64b465fd0d45e6fecb3ee801e6569b2a08142998bcd764c86310d08b14
+size 1768747

SoccerTwos/SoccerTwos-499728.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:838c38f27c6fb19615811871746089b40e9ab590a6fc13ad4692625ab3bc268e
+size 28431898

SoccerTwos/SoccerTwos-999874.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac4d1a0ef9ee911a4540d4c2b7084687377a47cdf130c2415b8ca0f400c09dbc
+size 1768747

SoccerTwos/SoccerTwos-999874.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eba822941b83c660c10bb8714b7d140f174c2205280bff083a391d35b9d77c35
+size 28431898

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9892a4ac5f8db19f402c3eae4b5305af8f0a679949c6b12c74204080dd326c
+size 28431030

SoccerTwos/events.out.tfevents.1711609094.workstation.4170.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8540bb2a28c6be567ea13c20c3aad533bae8e1d0de3d3f3f55f448c1a2da7470
+size 829570

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": 50000000, "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": "./trained-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": "SoccerTwos", "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: 50000000
+    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: ./trained-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: SoccerTwos
+  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 +1,268 @@
+Mono path[0] = '/home/node/WORK/WORKSPACE/TOOLS/ml-agents/trained-envs-executables/linux/SoccerTwos_Data/Managed'
+Mono config path = '/home/node/WORK/WORKSPACE/TOOLS/ml-agents/trained-envs-executables/linux/SoccerTwos_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+Display 0 '0': 3840x2160 (primary device).
+Display 1 'DELL U2718QM 28"': 3840x2160 (secondary device).
+Desktop is 3840 x 2160 @ 60 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/node/WORK/WORKSPACE/TOOLS/ml-agents/trained-envs-executables/linux/SoccerTwos_Data/UnitySubsystems
+GfxDevice: creating device client; threaded=1; jobified=0
+Renderer: Mesa Intel(R) UHD Graphics 630 (CFL 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_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_share
+d_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 10465088
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.054 seconds
+Default vsync count 1
+requesting resize 84 x 84
+resizing window to 84 x 84
+Desktop is 3840 x 2160 @ 60 Hz
+UnloadTime: 2.375277 ms
+Registered Communicator in Agent.
+Setting up 6 worker threads for Enlighten.
+requesting resize 84 x 84
+resizing window to 84 x 84
+Desktop is 3840 x 2160 @ 60 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

run_logs/timers.json

@@ -0,0 +1,403 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 3.2882423400878906,
+            "min": 3.28551983833313,
+            "max": 3.2957446575164795,
+            "count": 4
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 67974.546875,
+            "min": 61610.06640625,
+            "max": 105463.828125,
+            "count": 4
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 609.375,
+            "min": 605.1,
+            "max": 889.1666666666666,
+            "count": 4
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19500.0,
+            "min": 16868.0,
+            "max": 24204.0,
+            "count": 4
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1203.861183788245,
+            "min": 1200.7468599944746,
+            "max": 1203.9485920570594,
+            "count": 4
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 12038.611837882449,
+            "min": 2407.8971841141188,
+            "max": 14408.962319933695,
+            "count": 4
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 39014.0,
+            "min": 9122.0,
+            "max": 39014.0,
+            "count": 4
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 39014.0,
+            "min": 9122.0,
+            "max": 39014.0,
+            "count": 4
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.03001139871776104,
+            "min": 0.028771625831723213,
+            "max": 0.03587218374013901,
+            "count": 4
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 0.48018237948417664,
+            "min": 0.3164878785610199,
+            "max": 0.6098271012306213,
+            "count": 4
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.035965994000434875,
+            "min": 0.03436855971813202,
+            "max": 0.035965994000434875,
+            "count": 4
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 0.575455904006958,
+            "min": 0.3780541718006134,
+            "max": 0.6097903251647949,
+            "count": 4
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 4
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 4
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.19109999760985374,
+            "min": -0.2727272727272727,
+            "max": 0.19109999760985374,
+            "count": 4
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 3.05759996175766,
+            "min": -3.0,
+            "max": 3.05759996175766,
+            "count": 4
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.19109999760985374,
+            "min": -0.2727272727272727,
+            "max": 0.19109999760985374,
+            "count": 4
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 3.05759996175766,
+            "min": -3.0,
+            "max": 3.05759996175766,
+            "count": 4
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 4
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 4
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.01626398858303825,
+            "min": 0.01626398858303825,
+            "max": 0.01626398858303825,
+            "count": 1
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.01626398858303825,
+            "min": 0.01626398858303825,
+            "max": 0.01626398858303825,
+            "count": 1
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.0046758413780480625,
+            "min": 0.0046758413780480625,
+            "max": 0.0046758413780480625,
+            "count": 1
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.0046758413780480625,
+            "min": 0.0046758413780480625,
+            "max": 0.0046758413780480625,
+            "count": 1
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.004306589548165599,
+            "min": 0.004306589548165599,
+            "max": 0.004306589548165599,
+            "count": 1
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.004306589548165599,
+            "min": 0.004306589548165599,
+            "max": 0.004306589548165599,
+            "count": 1
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 1
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 1
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 1
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 1
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 1
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 1
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1711608727",
+        "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
+        "command_line_arguments": "/home/node/WORK/WORKSPACE/ENVS/miscs/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./trained-envs-executables/linux/SoccerTwos.x86_64 --run-id=SoccerTwos --force",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.2.1+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1711608804"
+    },
+    "total": 76.68805835700005,
+    "count": 1,
+    "self": 0.004073394999068114,
+    "children": {
+        "run_training.setup": {
+            "total": 0.018470230001184973,
+            "count": 1,
+            "self": 0.018470230001184973
+        },
+        "TrainerController.start_learning": {
+            "total": 76.66551473199979,
+            "count": 1,
+            "self": 0.06454389196915145,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 4.520945236999978,
+                    "count": 1,
+                    "self": 4.520945236999978
+                },
+                "TrainerController.advance": {
+                    "total": 71.92138248802985,
+                    "count": 3128,
+                    "self": 0.053513976990871015,
+                    "children": {
+                        "env_step": {
+                            "total": 44.710160134034595,
+                            "count": 3128,
+                            "self": 35.7539417990356,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 8.921819937015243,
+                                    "count": 3128,
+                                    "self": 0.2753146980085148,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 8.646505239006729,
+                                            "count": 6218,
+                                            "self": 8.646505239006729
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.03439839798375033,
+                                    "count": 3128,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 68.89855089398225,
+                                            "count": 3128,
+                                            "is_parallel": true,
+                                            "self": 39.51162345092598,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0017805160005082143,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.00041291399975307286,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0013676020007551415,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0013676020007551415
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.031287859999793,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00043526400077098515,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0005393470000853995,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0005393470000853995
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.028965359000721946,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.028965359000721946
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0013478899982146686,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00027469300221127924,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0010731969960033894,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0010731969960033894
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 29.386927443056265,
+                                                    "count": 3127,
+                                                    "is_parallel": true,
+                                                    "self": 1.519220111955292,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 1.035092900019663,
+                                                            "count": 3127,
+                                                            "is_parallel": true,
+                                                            "self": 1.035092900019663
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 21.991858610033887,
+                                                            "count": 3127,
+                                                            "is_parallel": true,
+                                                            "self": 21.991858610033887
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 4.8407558210474235,
+                                                            "count": 6254,
+                                                            "is_parallel": true,
+                                                            "self": 0.9229285281289776,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 3.917827292918446,
+                                                                    "count": 25016,
+                                                                    "is_parallel": true,
+                                                                    "self": 3.917827292918446
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 27.157708377004383,
+                            "count": 3128,
+                            "self": 0.48069884398864815,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 4.613371938014097,
+                                    "count": 3128,
+                                    "self": 4.613371938014097
+                                },
+                                "_update_policy": {
+                                    "total": 22.063637595001637,
+                                    "count": 2,
+                                    "self": 3.437678854994374,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 18.625958740007263,
+                                            "count": 44,
+                                            "self": 18.625958740007263
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.0200001270277426e-06,
+                    "count": 1,
+                    "self": 1.0200001270277426e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.15864209500068682,
+                    "count": 1,
+                    "self": 0.0011822640008176677,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.15745983099986915,
+                            "count": 1,
+                            "self": 0.15745983099986915
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,30 @@
+{
+    "SoccerTwos": {
+        "elo": 1204.8851687255153,
+        "checkpoints": [
+            {
+                "steps": 43014,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-43014.onnx",
+                "reward": null,
+                "creation_time": 1711608804.5854886,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-43014.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 43014,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": null,
+            "creation_time": 1711608804.5854886,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-43014.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.2.1+cu121"
+    }
+}