{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.5157133340835571, "min": 1.2935482263565063, "max": 3.2956314086914062, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 31720.849609375, "min": 20734.28515625, "max": 131043.8984375, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 91.54545454545455, "min": 39.274193548387096, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 20140.0, "min": 16360.0, "max": 23756.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1697.239423038248, "min": 1197.3130565395577, "max": 1750.4612546170524, "count": 4981 }, "SoccerTwos.Self-play.ELO.sum": { "value": 186696.33653420728, "min": 2394.6261130791154, "max": 408770.339808854, "count": 4981 }, "SoccerTwos.Step.mean": { "value": 49999932.0, "min": 9864.0, "max": 49999932.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999932.0, "min": 9864.0, "max": 49999932.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.06489232927560806, "min": -0.13828794658184052, "max": 0.183258056640625, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -7.138156414031982, "min": -27.519302368164062, "max": 27.974868774414062, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.06335005164146423, "min": -0.13755041360855103, "max": 0.1855001300573349, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -6.968505382537842, "min": -27.37253189086914, "max": 27.471893310546875, "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": -0.13321090719916603, "min": -0.48762353027568145, "max": 0.5933270269149059, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -14.653199791908264, "min": -64.33020031452179, "max": 65.97339940071106, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.13321090719916603, "min": -0.48762353027568145, "max": 0.5933270269149059, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -14.653199791908264, "min": -64.33020031452179, "max": 65.97339940071106, "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": 0.017387662552452336, "min": 0.008537781741082048, "max": 0.026532609233011803, "count": 2424 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017387662552452336, "min": 0.008537781741082048, "max": 0.026532609233011803, "count": 2424 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.08416157389680544, "min": 2.681433297766489e-05, "max": 0.13336161126693089, "count": 2424 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.08416157389680544, "min": 2.681433297766489e-05, "max": 0.13336161126693089, "count": 2424 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.08481311574578285, "min": 2.4318247657599083e-05, "max": 0.1360989545782407, "count": 2424 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.08481311574578285, "min": 2.4318247657599083e-05, "max": 0.1360989545782407, "count": 2424 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2424 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2424 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2424 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2424 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2424 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2424 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1675271541", "python_version": "3.10.6 (main, Nov 14 2022, 16:10:14) [GCC 11.3.0]", "command_line_arguments": "/home/ryan/hf-rl-u7/.venv/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTows.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": "1675515948" }, "total": 244406.351708607, "count": 1, "self": 0.6412395380320959, "children": { "run_training.setup": { "total": 0.024723760987399146, "count": 1, "self": 0.024723760987399146 }, "TrainerController.start_learning": { "total": 244405.68574530797, "count": 1, "self": 108.2894850797602, "children": { "TrainerController._reset_env": { "total": 7.761083504301496, "count": 250, "self": 7.761083504301496 }, "TrainerController.advance": { "total": 244289.24782776795, "count": 3442079, "self": 116.4954589283443, "children": { "env_step": { "total": 84596.5759572321, "count": 3442079, "self": 69675.5826231119, "children": { "SubprocessEnvManager._take_step": { "total": 14858.47143942205, "count": 3442079, "self": 694.5696085291856, "children": { "TorchPolicy.evaluate": { "total": 14163.901830892864, "count": 6279822, "self": 14163.901830892864 } } }, "workers": { "total": 62.52189469814766, "count": 3442079, "self": 0.0, "children": { "worker_root": { "total": 244215.29263141213, "count": 3442079, "is_parallel": true, "self": 186735.3678908844, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0025864450144581497, "count": 2, "is_parallel": true, "self": 0.0006178579933475703, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019685870211105794, "count": 8, "is_parallel": true, "self": 0.0019685870211105794 } } }, "UnityEnvironment.step": { "total": 0.032234045007498935, "count": 1, "is_parallel": true, "self": 0.000590939016547054, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0006142240017652512, "count": 1, "is_parallel": true, "self": 0.0006142240017652512 }, "communicator.exchange": { "total": 0.02902569100842811, "count": 1, "is_parallel": true, "self": 0.02902569100842811 }, "steps_from_proto": { "total": 0.002003190980758518, "count": 2, "is_parallel": true, "self": 0.0004106759442947805, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015925150364637375, "count": 8, "is_parallel": true, "self": 0.0015925150364637375 } } } } } } }, "UnityEnvironment.step": { "total": 57479.26351238892, "count": 3442078, "is_parallel": true, "self": 3500.0065727462643, "children": { "UnityEnvironment._generate_step_input": { "total": 2593.24616320472, "count": 3442078, "is_parallel": true, "self": 2593.24616320472 }, "communicator.exchange": { "total": 40589.26293149611, "count": 3442078, "is_parallel": true, "self": 40589.26293149611 }, "steps_from_proto": { "total": 10796.747844941827, "count": 6884156, "is_parallel": true, "self": 2144.1909672385955, "children": { "_process_rank_one_or_two_observation": { "total": 8652.556877703231, "count": 27536624, "is_parallel": true, "self": 8652.556877703231 } } } } }, "steps_from_proto": { "total": 0.6612281388079282, "count": 498, "is_parallel": true, "self": 0.13009566432447173, "children": { "_process_rank_one_or_two_observation": { "total": 0.5311324744834565, "count": 1992, "is_parallel": true, "self": 0.5311324744834565 } } } } } } } } }, "trainer_advance": { "total": 159576.1764116075, "count": 3442079, "self": 722.9643745862704, "children": { "process_trajectory": { "total": 20133.092868809617, "count": 3442079, "self": 20099.42255840465, "children": { "RLTrainer._checkpoint": { "total": 33.670310404966585, "count": 100, "self": 33.670310404966585 } } }, "_update_policy": { "total": 138720.11916821162, "count": 2424, "self": 10030.084023292206, "children": { "TorchPOCAOptimizer.update": { "total": 128690.03514491941, "count": 72720, "self": 128690.03514491941 } } } } } } }, "trainer_threads": { "total": 9.74978320300579e-07, "count": 1, "self": 9.74978320300579e-07 }, "TrainerController._save_models": { "total": 0.38734798098448664, "count": 1, "self": 0.0024687869590707123, "children": { "RLTrainer._checkpoint": { "total": 0.3848791940254159, "count": 1, "self": 0.3848791940254159 } } } } } } }