{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.3299667835235596, "min": 2.299405336380005, "max": 3.295668363571167, "count": 332 }, "SoccerTwos.Policy.Entropy.sum": { "value": 47121.25, "min": 15642.83203125, "max": 114542.3359375, "count": 332 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 50.76288659793814, "min": 42.76521739130435, "max": 999.0, "count": 332 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19696.0, "min": 15884.0, "max": 27488.0, "count": 332 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1478.026642524961, "min": 1179.7788040428786, "max": 1478.026642524961, "count": 325 }, "SoccerTwos.Self-play.ELO.sum": { "value": 286737.16864984244, "min": 2364.1918829443184, "max": 321863.026105703, "count": 325 }, "SoccerTwos.Step.mean": { "value": 3319968.0, "min": 9760.0, "max": 3319968.0, "count": 332 }, "SoccerTwos.Step.sum": { "value": 3319968.0, "min": 9760.0, "max": 3319968.0, "count": 332 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.13224956393241882, "min": -0.07247133553028107, "max": 0.17099936306476593, "count": 332 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 25.656415939331055, "min": -13.824865341186523, "max": 29.924888610839844, "count": 332 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.13362355530261993, "min": -0.06882161647081375, "max": 0.17515622079372406, "count": 332 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 25.922969818115234, "min": -13.692461013793945, "max": 30.6523380279541, "count": 332 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 332 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 332 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.08665361109468125, "min": -0.6923076923076923, "max": 0.5811499978105227, "count": 332 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 16.810800552368164, "min": -45.21120023727417, "max": 59.629999458789825, "count": 332 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.08665361109468125, "min": -0.6923076923076923, "max": 0.5811499978105227, "count": 332 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 16.810800552368164, "min": -45.21120023727417, "max": 59.629999458789825, "count": 332 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 332 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 332 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01647280962206423, "min": 0.010384321962677252, "max": 0.025824726539819192, "count": 157 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01647280962206423, "min": 0.010384321962677252, "max": 0.025824726539819192, "count": 157 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10077739705642065, "min": 0.0006277227638444553, "max": 0.11096864019831022, "count": 157 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10077739705642065, "min": 0.0006277227638444553, "max": 0.11096864019831022, "count": 157 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10252556800842286, "min": 0.0006187290273373947, "max": 0.11352627476056416, "count": 157 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10252556800842286, "min": 0.0006187290273373947, "max": 0.11352627476056416, "count": 157 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 157 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 157 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 157 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 157 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 157 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 157 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1724983919", "python_version": "3.10.12 (main, Jul 5 2023, 15:34:07) [Clang 14.0.6 ]", "command_line_arguments": "/Users/caio.campos/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.2", "numpy_version": "1.23.5", "end_time_seconds": "1725010048" }, "total": 26128.401052199, "count": 1, "self": 0.33014127099886537, "children": { "run_training.setup": { "total": 0.038303445999190444, "count": 1, "self": 0.038303445999190444 }, "TrainerController.start_learning": { "total": 26128.032607482, "count": 1, "self": 4.815222942630498, "children": { "TrainerController._reset_env": { "total": 8.892866306008727, "count": 17, "self": 8.892866306008727 }, "TrainerController.advance": { "total": 26114.05709432836, "count": 220564, "self": 4.818681626267789, "children": { "env_step": { "total": 20777.331596008145, "count": 220564, "self": 20038.60178467525, "children": { "SubprocessEnvManager._take_step": { "total": 735.6629285974359, "count": 220564, "self": 28.332394672645023, "children": { "TorchPolicy.evaluate": { "total": 707.3305339247909, "count": 423602, "self": 707.3305339247909 } } }, "workers": { "total": 3.06688273546024, "count": 220563, "self": 0.0, "children": { "worker_root": { "total": 26112.673646069434, "count": 220563, "is_parallel": true, "self": 6650.5135924498245, "children": { "steps_from_proto": { "total": 0.05718903701563249, "count": 34, "is_parallel": true, "self": 0.008453278995148139, "children": { "_process_rank_one_or_two_observation": { "total": 0.048735758020484354, "count": 136, "is_parallel": true, "self": 0.048735758020484354 } } }, "UnityEnvironment.step": { "total": 19462.102864582594, "count": 220563, "is_parallel": true, "self": 59.292598800391715, "children": { "UnityEnvironment._generate_step_input": { "total": 371.8948498334321, "count": 220563, "is_parallel": true, "self": 371.8948498334321 }, "communicator.exchange": { "total": 18326.88937894188, "count": 220563, "is_parallel": true, "self": 18326.88937894188 }, "steps_from_proto": { "total": 704.02603700689, "count": 441126, "is_parallel": true, "self": 94.92409573729674, "children": { "_process_rank_one_or_two_observation": { "total": 609.1019412695932, "count": 1764504, "is_parallel": true, "self": 609.1019412695932 } } } } } } } } } } }, "trainer_advance": { "total": 5331.906816693945, "count": 220563, "self": 39.04413141792611, "children": { "process_trajectory": { "total": 676.097296054013, "count": 220563, "self": 674.3273022760113, "children": { "RLTrainer._checkpoint": { "total": 1.7699937780016626, "count": 6, "self": 1.7699937780016626 } } }, "_update_policy": { "total": 4616.765389222006, "count": 158, "self": 473.07072151311513, "children": { "TorchPOCAOptimizer.update": { "total": 4143.694667708891, "count": 4740, "self": 4143.694667708891 } } } } } } }, "trainer_threads": { "total": 1.1279989848844707e-06, "count": 1, "self": 1.1279989848844707e-06 }, "TrainerController._save_models": { "total": 0.2674227770039579, "count": 1, "self": 0.0017639980069361627, "children": { "RLTrainer._checkpoint": { "total": 0.2656587789970217, "count": 1, "self": 0.2656587789970217 } } } } } } }