{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.0960352420806885, "min": 3.0896952152252197, "max": 3.0960352420806885, "count": 2 }, "SoccerTwos.Policy.Entropy.sum": { "value": 63505.875, "min": 63505.875, "max": 92740.2890625, "count": 2 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 299.36842105263156, "min": 152.3125, "max": 299.36842105263156, "count": 2 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 22752.0, "min": 19496.0, "max": 22752.0, "count": 2 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1230.9014358662068, "min": 1229.4453333681085, "max": 1230.9014358662068, "count": 2 }, "SoccerTwos.Self-play.ELO.sum": { "value": 41850.64881945103, "min": 41850.64881945103, "max": 78684.50133555895, "count": 2 }, "SoccerTwos.Step.mean": { "value": 2019628.0, "min": 2009760.0, "max": 2019628.0, "count": 2 }, "SoccerTwos.Step.sum": { "value": 2019628.0, "min": 2009760.0, "max": 2019628.0, "count": 2 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.046337660402059555, "min": 0.046337660402059555, "max": 0.07532840222120285, "count": 2 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 1.7144933938980103, "min": 1.7144933938980103, "max": 4.745689392089844, "count": 2 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.04667149856686592, "min": 0.04667149856686592, "max": 0.07894717901945114, "count": 2 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 1.726845383644104, "min": 1.726845383644104, "max": 4.973672389984131, "count": 2 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 2 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.2555135101885409, "min": -0.019536508454216853, "max": 0.2555135101885409, "count": 2 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 9.453999876976013, "min": -1.2308000326156616, "max": 9.453999876976013, "count": 2 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.2555135101885409, "min": -0.019536508454216853, "max": 0.2555135101885409, "count": 2 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 9.453999876976013, "min": -1.2308000326156616, "max": 9.453999876976013, "count": 2 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 2 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691424083", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/linux/SoccerTwos/SoccerTwos --run-id=SoccerTwos_Colab_02 --no-graphics --resume", "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": "1691424192" }, "total": 109.55755164400034, "count": 1, "self": 0.008397847001106129, "children": { "run_training.setup": { "total": 0.083337637999648, "count": 1, "self": 0.083337637999648 }, "TrainerController.start_learning": { "total": 109.46581615899959, "count": 1, "self": 0.08752070202899631, "children": { "TrainerController._reset_env": { "total": 2.5959777920015767, "count": 2, "self": 2.5959777920015767 }, "TrainerController.advance": { "total": 105.89369049796733, "count": 1620, "self": 0.0788498220317706, "children": { "env_step": { "total": 60.58236003895581, "count": 1620, "self": 50.4488764498783, "children": { "SubprocessEnvManager._take_step": { "total": 10.08933123008319, "count": 1620, "self": 0.4305625380766287, "children": { "TorchPolicy.evaluate": { "total": 9.65876869200656, "count": 3158, "self": 9.65876869200656 } } }, "workers": { "total": 0.04415235899432446, "count": 1620, "self": 0.0, "children": { "worker_root": { "total": 74.08534333506941, "count": 1620, "is_parallel": true, "self": 32.6645744430607, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007715671001278679, "count": 2, "is_parallel": true, "self": 0.0019651969996630214, "children": { "_process_rank_one_or_two_observation": { "total": 0.0057504740016156575, "count": 8, "is_parallel": true, "self": 0.0057504740016156575 } } }, "UnityEnvironment.step": { "total": 0.10233237800093775, "count": 1, "is_parallel": true, "self": 0.0017222620008396916, "children": { "UnityEnvironment._generate_step_input": { "total": 0.001153119999798946, "count": 1, "is_parallel": true, "self": 0.001153119999798946 }, "communicator.exchange": { "total": 0.09257872399939515, "count": 1, "is_parallel": true, "self": 0.09257872399939515 }, "steps_from_proto": { "total": 0.006878272000903962, "count": 2, "is_parallel": true, "self": 0.0009336610000900691, "children": { "_process_rank_one_or_two_observation": { "total": 0.005944611000813893, "count": 8, "is_parallel": true, "self": 0.005944611000813893 } } } } } } }, "steps_from_proto": { "total": 0.004856255996855907, "count": 2, "is_parallel": true, "self": 0.0010124789969268022, "children": { "_process_rank_one_or_two_observation": { "total": 0.003843776999929105, "count": 8, "is_parallel": true, "self": 0.003843776999929105 } } }, "UnityEnvironment.step": { "total": 41.41591263601185, "count": 1619, "is_parallel": true, "self": 2.4258105140743282, "children": { "UnityEnvironment._generate_step_input": { "total": 1.3363438629930897, "count": 1619, "is_parallel": true, "self": 1.3363438629930897 }, "communicator.exchange": { "total": 30.036212177003108, "count": 1619, "is_parallel": true, "self": 30.036212177003108 }, "steps_from_proto": { "total": 7.617546081941327, "count": 3238, "is_parallel": true, "self": 1.3740259158912522, "children": { "_process_rank_one_or_two_observation": { "total": 6.243520166050075, "count": 12952, "is_parallel": true, "self": 6.243520166050075 } } } } } } } } } } }, "trainer_advance": { "total": 45.232480636979744, "count": 1620, "self": 0.6351825480069238, "children": { "process_trajectory": { "total": 11.586294170972906, "count": 1620, "self": 11.586294170972906 }, "_update_policy": { "total": 33.011003917999915, "count": 1, "self": 1.4462389879990951, "children": { "TorchPOCAOptimizer.update": { "total": 31.56476493000082, "count": 9, "self": 31.56476493000082 } } } } } } }, "trainer_threads": { "total": 2.3910015443107113e-06, "count": 1, "self": 2.3910015443107113e-06 }, "TrainerController._save_models": { "total": 0.8886247760001424, "count": 1, "self": 0.004244113000822836, "children": { "RLTrainer._checkpoint": { "total": 0.8843806629993196, "count": 1, "self": 0.8843806629993196 } } } } } } }