{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.3866503238677979, "min": 1.2979317903518677, "max": 3.2957231998443604, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 27289.27734375, "min": 23159.306640625, "max": 106430.734375, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 61.6625, "min": 39.26984126984127, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19732.0, "min": 13252.0, "max": 28120.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1828.025269199515, "min": 1197.0379398352115, "max": 1834.7630645192041, "count": 4999 }, "SoccerTwos.Self-play.ELO.sum": { "value": 292484.0430719224, "min": 2396.5231543014306, "max": 411149.350861825, "count": 4999 }, "SoccerTwos.Step.mean": { "value": 49999972.0, "min": 9080.0, "max": 49999972.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999972.0, "min": 9080.0, "max": 49999972.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.01768748089671135, "min": -0.14829443395137787, "max": 0.25545018911361694, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.8299970626831055, "min": -28.769119262695312, "max": 24.469852447509766, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.017318900674581528, "min": -0.1497812718153, "max": 0.2554108798503876, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -2.771024227142334, "min": -29.057567596435547, "max": 26.165250778198242, "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": -0.12839374840259551, "min": -0.5857999987072415, "max": 0.6214795437726107, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -20.542999744415283, "min": -67.09439992904663, "max": 58.69279932975769, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.12839374840259551, "min": -0.5857999987072415, "max": 0.6214795437726107, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -20.542999744415283, "min": -67.09439992904663, "max": 58.69279932975769, "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": 0.018115490095078714, "min": 0.00907405869026358, "max": 0.025428198114968836, "count": 2426 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018115490095078714, "min": 0.00907405869026358, "max": 0.025428198114968836, "count": 2426 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10066991746425628, "min": 0.001378662643643717, "max": 0.12973978693286578, "count": 2426 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10066991746425628, "min": 0.001378662643643717, "max": 0.12973978693286578, "count": 2426 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.1012613445520401, "min": 0.001378152430212746, "max": 0.13283031284809113, "count": 2426 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.1012613445520401, "min": 0.001378152430212746, "max": 0.13283031284809113, "count": 2426 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2426 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2426 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2426 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 2426 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2426 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 2426 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1728527999", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/juu/anaconda3/envs/drl3_12/bin/mlagents-learn ml-agents/config/poca/SoccerTwos.yaml --env=ml-agents/training-envs-executables/linux/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwo --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.0+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1728563849" }, "total": 35849.872272676, "count": 1, "self": 0.1666019420081284, "children": { "run_training.setup": { "total": 0.011546531999556464, "count": 1, "self": 0.011546531999556464 }, "TrainerController.start_learning": { "total": 35849.694124202, "count": 1, "self": 36.143399278240395, "children": { "TrainerController._reset_env": { "total": 2.9661042849256773, "count": 250, "self": 2.9661042849256773 }, "TrainerController.advance": { "total": 35810.51599326883, "count": 3451058, "self": 32.35448769282084, "children": { "env_step": { "total": 27282.7926643451, "count": 3451058, "self": 19891.24456093924, "children": { "SubprocessEnvManager._take_step": { "total": 7368.746740459837, "count": 3451058, "self": 209.01907084547747, "children": { "TorchPolicy.evaluate": { "total": 7159.72766961436, "count": 6277112, "self": 7159.72766961436 } } }, "workers": { "total": 22.801362946020163, "count": 3451058, "self": 0.0, "children": { "worker_root": { "total": 35790.08399832593, "count": 3451058, "is_parallel": true, "self": 19715.142423910747, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010994280000886647, "count": 2, "is_parallel": true, "self": 0.0002463939981680596, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008530340019206051, "count": 8, "is_parallel": true, "self": 0.0008530340019206051 } } }, "UnityEnvironment.step": { "total": 0.01159899499907624, "count": 1, "is_parallel": true, "self": 0.0002746959999058163, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000218371998926159, "count": 1, "is_parallel": true, "self": 0.000218371998926159 }, "communicator.exchange": { "total": 0.010385640000095009, "count": 1, "is_parallel": true, "self": 0.010385640000095009 }, "steps_from_proto": { "total": 0.0007202870001492556, "count": 2, "is_parallel": true, "self": 0.00014195000039762817, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005783369997516274, "count": 8, "is_parallel": true, "self": 0.0005783369997516274 } } } } } } }, "UnityEnvironment.step": { "total": 16074.762984299196, "count": 3451057, "is_parallel": true, "self": 902.0901281111073, "children": { "UnityEnvironment._generate_step_input": { "total": 508.2599889366302, "count": 3451057, "is_parallel": true, "self": 508.2599889366302 }, "communicator.exchange": { "total": 12291.794342749032, "count": 3451057, "is_parallel": true, "self": 12291.794342749032 }, "steps_from_proto": { "total": 2372.618524502426, "count": 6902114, "is_parallel": true, "self": 448.1486609659878, "children": { "_process_rank_one_or_two_observation": { "total": 1924.4698635364384, "count": 27608456, "is_parallel": true, "self": 1924.4698635364384 } } } } }, "steps_from_proto": { "total": 0.17859011598557117, "count": 498, "is_parallel": true, "self": 0.03393091395810188, "children": { "_process_rank_one_or_two_observation": { "total": 0.1446592020274693, "count": 1992, "is_parallel": true, "self": 0.1446592020274693 } } } } } } } } }, "trainer_advance": { "total": 8495.368841230913, "count": 3451058, "self": 264.4522677945988, "children": { "process_trajectory": { "total": 4058.7985299343854, "count": 3451058, "self": 4051.5498065993543, "children": { "RLTrainer._checkpoint": { "total": 7.248723335031173, "count": 100, "self": 7.248723335031173 } } }, "_update_policy": { "total": 4172.118043501929, "count": 2426, "self": 2557.479283258461, "children": { "TorchPOCAOptimizer.update": { "total": 1614.638760243468, "count": 72780, "self": 1614.638760243468 } } } } } } }, "trainer_threads": { "total": 4.760004230774939e-07, "count": 1, "self": 4.760004230774939e-07 }, "TrainerController._save_models": { "total": 0.06862689399713418, "count": 1, "self": 0.0009139159956248477, "children": { "RLTrainer._checkpoint": { "total": 0.06771297800150933, "count": 1, "self": 0.06771297800150933 } } } } } } }