{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.252577781677246, "min": 3.1191282272338867, "max": 3.2952306270599365, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 146339.984375, "min": 24855.20703125, "max": 1063542.25, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 380.2142857142857, "min": 71.87037037037037, "max": 625.5, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 21292.0, "min": 14188.0, "max": 26148.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1178.6458152441182, "min": 1159.6035774787774, "max": 1204.9010648674673, "count": 499 }, "SoccerTwos.Self-play.ELO.sum": { "value": 18858.333043905892, "min": 2327.4492362180363, "max": 86356.93565384974, "count": 499 }, "SoccerTwos.Step.mean": { "value": 4999602.0, "min": 9892.0, "max": 4999602.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999602.0, "min": 9892.0, "max": 4999602.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.2253483682870865, "min": -0.46143394708633423, "max": 0.02706277370452881, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -5.859057426452637, "min": -45.84828186035156, "max": 2.5980262756347656, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.2253483682870865, "min": -0.46143394708633423, "max": 0.02706277370452881, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -5.859057426452637, "min": -45.84828186035156, "max": 2.5980262756347656, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.3256230790597888, "min": -0.5567310349694614, "max": 0.28976000177984435, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -8.46620005555451, "min": -22.83959996700287, "max": 10.30999992787838, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.3256230790597888, "min": -0.5567310349694614, "max": 0.28976000177984435, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -8.46620005555451, "min": -22.83959996700287, "max": 10.30999992787838, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.1596376054920256, "min": 0.08458976991241798, "max": 0.23267643476525943, "count": 310 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.1596376054920256, "min": 0.08458976991241798, "max": 0.23267643476525943, "count": 310 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.007365186830187062, "min": 0.0016683316580232107, "max": 0.05216269002606471, "count": 310 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.007365186830187062, "min": 0.0016683316580232107, "max": 0.05216269002606471, "count": 310 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.007365186830187062, "min": 0.0016683316580232107, "max": 0.05236586214353641, "count": 310 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.007365186830187062, "min": 0.0016683316580232107, "max": 0.05236586214353641, "count": 310 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 310 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 310 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 310 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.2, "max": 0.20000000000000007, "count": 310 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 310 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 310 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1684077500", "python_version": "3.9.16 (main, Mar 8 2023, 14:00:05) \n[GCC 11.2.0]", "command_line_arguments": "/home/miki/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos-v3.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos-v3 --no-graphics --force --num-envs=24", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0", "numpy_version": "1.19.5", "end_time_seconds": "1684092796" }, "total": 15295.404105814, "count": 1, "self": 1.0446043089978048, "children": { "run_training.setup": { "total": 0.09455194499969366, "count": 1, "self": 0.09455194499969366 }, "TrainerController.start_learning": { "total": 15294.264949560002, "count": 1, "self": 4.225329163004062, "children": { "TrainerController._reset_env": { "total": 182.97077149601319, "count": 99, "self": 182.97077149601319 }, "TrainerController.advance": { "total": 15103.868332486985, "count": 74207, "self": 2.2018525988787587, "children": { "env_step": { "total": 12338.052529185657, "count": 74207, "self": 2679.6467814085954, "children": { "SubprocessEnvManager._take_step": { "total": 9652.353870569023, "count": 1120006, "self": 195.04583905737672, "children": { "TorchPolicy.evaluate": { "total": 9457.308031511646, "count": 2222222, "self": 9457.308031511646 } } }, "workers": { "total": 6.051877208039514, "count": 74207, "self": 0.0, "children": { "worker_root": { "total": 366760.6878665271, "count": 1119717, "is_parallel": true, "self": 354767.21357168874, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.12077161001434433, "count": 48, "is_parallel": true, "self": 0.02077655497851083, "children": { "_process_rank_one_or_two_observation": { "total": 0.0999950550358335, "count": 192, "is_parallel": true, "self": 0.0999950550358335 } } }, "UnityEnvironment.step": { "total": 0.6189754869992612, "count": 24, "is_parallel": true, "self": 0.01480950100813061, "children": { "UnityEnvironment._generate_step_input": { "total": 0.01281962700522854, "count": 24, "is_parallel": true, "self": 0.01281962700522854 }, "communicator.exchange": { "total": 0.508901249995688, "count": 24, "is_parallel": true, "self": 0.508901249995688 }, "steps_from_proto": { "total": 0.08244510899021407, "count": 48, "is_parallel": true, "self": 0.012597975994140143, "children": { "_process_rank_one_or_two_observation": { "total": 0.06984713299607392, "count": 192, "is_parallel": true, "self": 0.06984713299607392 } } } } } } }, "UnityEnvironment.step": { "total": 11949.40095527341, "count": 1119693, "is_parallel": true, "self": 583.9515308141708, "children": { "UnityEnvironment._generate_step_input": { "total": 631.2777412939067, "count": 1119693, "is_parallel": true, "self": 631.2777412939067 }, "communicator.exchange": { "total": 7421.867804270238, "count": 1119693, "is_parallel": true, "self": 7421.867804270238 }, "steps_from_proto": { "total": 3312.3038788950944, "count": 2239386, "is_parallel": true, "self": 457.2370621924092, "children": { "_process_rank_one_or_two_observation": { "total": 2855.066816702685, "count": 8957544, "is_parallel": true, "self": 2855.066816702685 } } } } }, "steps_from_proto": { "total": 44.073339564944035, "count": 4704, "is_parallel": true, "self": 4.9122428541049885, "children": { "_process_rank_one_or_two_observation": { "total": 39.16109671083905, "count": 18816, "is_parallel": true, "self": 39.16109671083905 } } } } } } } } }, "trainer_advance": { "total": 2763.613950702449, "count": 74207, "self": 60.953024242564425, "children": { "process_trajectory": { "total": 1127.0298015669614, "count": 74207, "self": 1098.0917893119658, "children": { "RLTrainer._checkpoint": { "total": 28.938012254995556, "count": 10, "self": 28.938012254995556 } } }, "_update_policy": { "total": 1575.6311248929233, "count": 310, "self": 134.97924930170848, "children": { "TorchPOCAOptimizer.update": { "total": 1440.6518755912148, "count": 9303, "self": 1440.6518755912148 } } } } } } }, "trainer_threads": { "total": 8.269998943433166e-07, "count": 1, "self": 8.269998943433166e-07 }, "TrainerController._save_models": { "total": 3.200515586999245, "count": 1, "self": 0.17947952200483996, "children": { "RLTrainer._checkpoint": { "total": 3.021036064994405, "count": 1, "self": 3.021036064994405 } } } } } } }