{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.9322335720062256, "min": 2.927135467529297, "max": 3.2956697940826416, "count": 479 }, "SoccerTwos.Policy.Entropy.sum": { "value": 58926.16796875, "min": 7677.369140625, "max": 146924.84375, "count": 479 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 120.64102564102564, "min": 120.64102564102564, "max": 999.0, "count": 479 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 18820.0, "min": 10080.0, "max": 30796.0, "count": 479 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1285.6498803825195, "min": 1178.2738793012145, "max": 1287.0628408087123, "count": 329 }, "SoccerTwos.Self-play.ELO.sum": { "value": 100280.69066983652, "min": 2356.547758602429, "max": 108969.56266498024, "count": 329 }, "SoccerTwos.Step.mean": { "value": 4789974.0, "min": 9198.0, "max": 4789974.0, "count": 479 }, "SoccerTwos.Step.sum": { "value": 4789974.0, "min": 9198.0, "max": 4789974.0, "count": 479 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.08229371905326843, "min": -0.04906930774450302, "max": 0.14260533452033997, "count": 479 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 6.336616516113281, "min": -0.8340321779251099, "max": 9.733957290649414, "count": 479 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0940345823764801, "min": -0.04911098629236221, "max": 0.1348666250705719, "count": 479 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 7.240662574768066, "min": -0.8347645998001099, "max": 9.857460975646973, "count": 479 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 479 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 479 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.20396883301920704, "min": -0.7105294115403119, "max": 0.5933759999275208, "count": 479 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 15.705600142478943, "min": -24.157999992370605, "max": 27.86119994521141, "count": 479 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.20396883301920704, "min": -0.7105294115403119, "max": 0.5933759999275208, "count": 479 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 15.705600142478943, "min": -24.157999992370605, "max": 27.86119994521141, "count": 479 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 479 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 479 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.018621201223383347, "min": 0.009866767615494609, "max": 0.024412265633388112, "count": 222 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.018621201223383347, "min": 0.009866767615494609, "max": 0.024412265633388112, "count": 222 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.03903478905558586, "min": 1.160255315824088e-07, "max": 0.03942800971368949, "count": 222 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.03903478905558586, "min": 1.160255315824088e-07, "max": 0.03942800971368949, "count": 222 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.0406762929012378, "min": 1.9420921783345573e-07, "max": 0.0406762929012378, "count": 222 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.0406762929012378, "min": 1.9420921783345573e-07, "max": 0.0406762929012378, "count": 222 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 222 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 222 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 222 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 222 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 222 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 222 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687076328", "python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:39:03) \n[GCC 11.3.0]", "command_line_arguments": "/rapid_data/dhruv/micromamba/envs/drl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/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": "1687151245" }, "total": 74917.00693269074, "count": 1, "self": 0.03509733825922012, "children": { "run_training.setup": { "total": 0.03303243964910507, "count": 1, "self": 0.03303243964910507 }, "TrainerController.start_learning": { "total": 74916.93880291283, "count": 1, "self": 10.035071581602097, "children": { "TrainerController._reset_env": { "total": 4.138245269656181, "count": 14, "self": 4.138245269656181 }, "TrainerController.advance": { "total": 74900.42200507969, "count": 308540, "self": 10.115174554288387, "children": { "env_step": { "total": 8203.583398371935, "count": 308540, "self": 6515.309337794781, "children": { "SubprocessEnvManager._take_step": { "total": 1681.8731979727745, "count": 308540, "self": 70.17630571126938, "children": { "TorchPolicy.evaluate": { "total": 1611.6968922615051, "count": 611386, "self": 1611.6968922615051 } } }, "workers": { "total": 6.400862604379654, "count": 308539, "self": 0.0, "children": { "worker_root": { "total": 74895.62556742877, "count": 308539, "is_parallel": true, "self": 69616.0502769649, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003817640244960785, "count": 2, "is_parallel": true, "self": 0.0009641647338867188, "children": { "_process_rank_one_or_two_observation": { "total": 0.002853475511074066, "count": 8, "is_parallel": true, "self": 0.002853475511074066 } } }, "UnityEnvironment.step": { "total": 0.03977087140083313, "count": 1, "is_parallel": true, "self": 0.0007498785853385925, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0007988587021827698, "count": 1, "is_parallel": true, "self": 0.0007988587021827698 }, "communicator.exchange": { "total": 0.03596772998571396, "count": 1, "is_parallel": true, "self": 0.03596772998571396 }, "steps_from_proto": { "total": 0.002254404127597809, "count": 2, "is_parallel": true, "self": 0.000506080687046051, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017483234405517578, "count": 8, "is_parallel": true, "self": 0.0017483234405517578 } } } } } } }, "UnityEnvironment.step": { "total": 5279.544272713363, "count": 308538, "is_parallel": true, "self": 244.2109673321247, "children": { "UnityEnvironment._generate_step_input": { "total": 160.03656523674726, "count": 308538, "is_parallel": true, "self": 160.03656523674726 }, "communicator.exchange": { "total": 4166.491050496697, "count": 308538, "is_parallel": true, "self": 4166.491050496697 }, "steps_from_proto": { "total": 708.8056896477938, "count": 617076, "is_parallel": true, "self": 159.4736889153719, "children": { "_process_rank_one_or_two_observation": { "total": 549.3320007324219, "count": 2468304, "is_parallel": true, "self": 549.3320007324219 } } } } }, "steps_from_proto": { "total": 0.03101775050163269, "count": 26, "is_parallel": true, "self": 0.007285363972187042, "children": { "_process_rank_one_or_two_observation": { "total": 0.023732386529445648, "count": 104, "is_parallel": true, "self": 0.023732386529445648 } } } } } } } } }, "trainer_advance": { "total": 66686.72343215346, "count": 308539, "self": 107.34100019186735, "children": { "process_trajectory": { "total": 56687.7143227607, "count": 308539, "self": 56668.0476122126, "children": { "RLTrainer._checkpoint": { "total": 19.666710548102856, "count": 9, "self": 19.666710548102856 } } }, "_update_policy": { "total": 9891.668109200895, "count": 222, "self": 1115.7652814388275, "children": { "TorchPOCAOptimizer.update": { "total": 8775.902827762067, "count": 6666, "self": 8775.902827762067 } } } } } } }, "trainer_threads": { "total": 1.30385160446167e-06, "count": 1, "self": 1.30385160446167e-06 }, "TrainerController._save_models": { "total": 2.3434796780347824, "count": 1, "self": 0.12060417979955673, "children": { "RLTrainer._checkpoint": { "total": 2.2228754982352257, "count": 1, "self": 2.2228754982352257 } } } } } } }