{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4118643999099731, "min": 1.334549069404602, "max": 3.2957675457000732, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 28689.083984375, "min": 16186.33203125, "max": 140877.703125, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 70.73239436619718, "min": 44.14545454545455, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20088.0, "min": 14016.0, "max": 25436.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1757.1116673539389, "min": 1196.4770090911709, "max": 1819.6628678182683, "count": 3779 }, "SoccerTwos.Self-play.ELO.sum": { "value": 249509.8567642593, "min": 2392.9540181823418, "max": 381723.31539122155, "count": 3779 }, "SoccerTwos.Step.mean": { "value": 49999992.0, "min": 9734.0, "max": 49999992.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999992.0, "min": 9734.0, "max": 49999992.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.039098095148801804, "min": -0.13506445288658142, "max": 0.21278829872608185, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -5.512831211090088, "min": -23.636280059814453, "max": 24.306732177734375, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.04226994141936302, "min": -0.1335238367319107, "max": 0.21495413780212402, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -5.960061550140381, "min": -23.366670608520508, "max": 24.093002319335938, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.051009929349236455, "min": -0.5, "max": 0.7483039258741865, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 7.19240003824234, "min": -68.52999997138977, "max": 76.32700043916702, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.051009929349236455, "min": -0.5, "max": 0.7483039258741865, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 7.19240003824234, "min": -68.52999997138977, "max": 76.32700043916702, "count": 5000 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 5000 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01817262122640386, "min": 0.010402236335600416, "max": 0.0282656139228493, "count": 2387 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01817262122640386, "min": 0.010402236335600416, "max": 0.0282656139228493, "count": 2387 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09874455779790878, "min": 3.9828985306615085e-11, "max": 0.11980765188733737, "count": 2387 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09874455779790878, "min": 3.9828985306615085e-11, "max": 0.11980765188733737, "count": 2387 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10047606552640596, "min": 6.236301995643511e-11, "max": 0.12174425944685936, "count": 2387 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10047606552640596, "min": 6.236301995643511e-11, "max": 0.12174425944685936, "count": 2387 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2387 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2387 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2387 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2387 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2387 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2387 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1679462454", "python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:39:03) \n[GCC 11.3.0]", "command_line_arguments": "/media/hd/work/hf-rl-u7/_conda/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1679553317" }, "total": 90863.07966329798, "count": 1, "self": 0.32276201294735074, "children": { "run_training.setup": { "total": 0.011372299981303513, "count": 1, "self": 0.011372299981303513 }, "TrainerController.start_learning": { "total": 90862.74552898505, "count": 1, "self": 75.61205475765746, "children": { "TrainerController._reset_env": { "total": 12.571995195932686, "count": 250, "self": 12.571995195932686 }, "TrainerController.advance": { "total": 90774.25577048131, "count": 3382945, "self": 69.5784866772592, "children": { "env_step": { "total": 70906.86568981281, "count": 3382945, "self": 56689.131164202816, "children": { "SubprocessEnvManager._take_step": { "total": 14170.955866511795, "count": 3382945, "self": 408.64297854085453, "children": { "TorchPolicy.evaluate": { "total": 13762.31288797094, "count": 6333988, "self": 13762.31288797094 } } }, "workers": { "total": 46.77865909819957, "count": 3382945, "self": 0.0, "children": { "worker_root": { "total": 90730.07692549855, "count": 3382945, "is_parallel": true, "self": 42695.56536559318, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022973798913881183, "count": 2, "is_parallel": true, "self": 0.0005886418512091041, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017087380401790142, "count": 8, "is_parallel": true, "self": 0.0017087380401790142 } } }, "UnityEnvironment.step": { "total": 0.0332693139789626, "count": 1, "is_parallel": true, "self": 0.0005849449662491679, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0009517880389466882, "count": 1, "is_parallel": true, "self": 0.0009517880389466882 }, "communicator.exchange": { "total": 0.02957025996875018, "count": 1, "is_parallel": true, "self": 0.02957025996875018 }, "steps_from_proto": { "total": 0.0021623210050165653, "count": 2, "is_parallel": true, "self": 0.00044048589188605547, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017218351131305099, "count": 8, "is_parallel": true, "self": 0.0017218351131305099 } } } } } } }, "UnityEnvironment.step": { "total": 48033.7887676236, "count": 3382944, "is_parallel": true, "self": 2896.6152998108882, "children": { "UnityEnvironment._generate_step_input": { "total": 2069.945759323309, "count": 3382944, "is_parallel": true, "self": 2069.945759323309 }, "communicator.exchange": { "total": 34645.29802252329, "count": 3382944, "is_parallel": true, "self": 34645.29802252329 }, "steps_from_proto": { "total": 8421.929685966112, "count": 6765888, "is_parallel": true, "self": 1677.9999219384044, "children": { "_process_rank_one_or_two_observation": { "total": 6743.929764027707, "count": 27063552, "is_parallel": true, "self": 6743.929764027707 } } } } }, "steps_from_proto": { "total": 0.7227922817692161, "count": 498, "is_parallel": true, "self": 0.14150283834896982, "children": { "_process_rank_one_or_two_observation": { "total": 0.5812894434202462, "count": 1992, "is_parallel": true, "self": 0.5812894434202462 } } } } } } } } }, "trainer_advance": { "total": 19797.81159399124, "count": 3382945, "self": 501.774446016876, "children": { "process_trajectory": { "total": 6671.715125667397, "count": 3382945, "self": 6639.40557174827, "children": { "RLTrainer._checkpoint": { "total": 32.30955391912721, "count": 100, "self": 32.30955391912721 } } }, "_update_policy": { "total": 12624.322022306966, "count": 2387, "self": 7249.404454407631, "children": { "TorchPOCAOptimizer.update": { "total": 5374.917567899334, "count": 71610, "self": 5374.917567899334 } } } } } } }, "trainer_threads": { "total": 6.580958142876625e-07, "count": 1, "self": 6.580958142876625e-07 }, "TrainerController._save_models": { "total": 0.3057078920537606, "count": 1, "self": 0.001581975957378745, "children": { "RLTrainer._checkpoint": { "total": 0.30412591609638184, "count": 1, "self": 0.30412591609638184 } } } } } } }