{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.4418904781341553, "min": 1.294468879699707, "max": 3.295708417892456, "count": 5000 }, "SoccerTwos.Policy.Entropy.sum": { "value": 29437.63671875, "min": 14215.28125, "max": 121718.203125, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 71.55072463768116, "min": 42.12931034482759, "max": 999.0, "count": 5000 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19748.0, "min": 5236.0, "max": 31520.0, "count": 5000 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1709.4221979716372, "min": 1195.0008864310503, "max": 1828.1590152058777, "count": 4889 }, "SoccerTwos.Self-play.ELO.sum": { "value": 235900.26332008594, "min": 2391.080746409615, "max": 390501.0282857622, "count": 4889 }, "SoccerTwos.Step.mean": { "value": 49999811.0, "min": 9140.0, "max": 49999811.0, "count": 5000 }, "SoccerTwos.Step.sum": { "value": 49999811.0, "min": 9140.0, "max": 49999811.0, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.07240379601716995, "min": -0.1420961320400238, "max": 0.13643905520439148, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -9.991724014282227, "min": -21.80714988708496, "max": 25.104785919189453, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.07276814430952072, "min": -0.14439648389816284, "max": 0.13277669250965118, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -10.042003631591797, "min": -22.374191284179688, "max": 24.291780471801758, "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": -0.15703623018402985, "min": -0.5660000017711094, "max": 0.36306666400697496, "count": 5000 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -21.670999765396118, "min": -65.9384001493454, "max": 49.36360025405884, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.15703623018402985, "min": -0.5660000017711094, "max": 0.36306666400697496, "count": 5000 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -21.670999765396118, "min": -65.9384001493454, "max": 49.36360025405884, "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": 0.015481926136029263, "min": 0.01054826683345406, "max": 0.025319085903659774, "count": 2419 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.015481926136029263, "min": 0.01054826683345406, "max": 0.025319085903659774, "count": 2419 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.07773154104749362, "min": 8.310707263111302e-09, "max": 0.11789453849196434, "count": 2419 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.07773154104749362, "min": 8.310707263111302e-09, "max": 0.11789453849196434, "count": 2419 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.07860433558622996, "min": 1.0615595454529133e-08, "max": 0.12032449394464492, "count": 2419 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.07860433558622996, "min": 1.0615595454529133e-08, "max": 0.12032449394464492, "count": 2419 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2419 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 2419 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 2419 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.19999999999999996, "max": 0.20000000000000007, "count": 2419 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2419 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005, "max": 0.005000000000000001, "count": 2419 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1696248227", "python_version": "3.9.0 (default, Nov 15 2020, 06:25:35) \n[Clang 10.0.0 ]", "command_line_arguments": "/Users/malanevans/miniconda3-intel/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --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", "numpy_version": "1.21.2", "end_time_seconds": "1696465673" }, "total": 217441.771066791, "count": 1, "self": 1.445043290994363, "children": { "run_training.setup": { "total": 0.03292408299999994, "count": 1, "self": 0.03292408299999994 }, "TrainerController.start_learning": { "total": 217440.293099417, "count": 1, "self": 52.59163497935515, "children": { "TrainerController._reset_env": { "total": 14.288498456003614, "count": 250, "self": 14.288498456003614 }, "TrainerController.advance": { "total": 217373.28344910764, "count": 3424690, "self": 47.21728044716292, "children": { "env_step": { "total": 43908.40828150283, "count": 3424690, "self": 35030.082407733455, "children": { "SubprocessEnvManager._take_step": { "total": 8844.015071889033, "count": 3424690, "self": 235.24708809384538, "children": { "TorchPolicy.evaluate": { "total": 8608.767983795187, "count": 6285530, "self": 8608.767983795187 } } }, "workers": { "total": 34.31080188034706, "count": 3424690, "self": 0.0, "children": { "worker_root": { "total": 217355.6228162299, "count": 3424690, "is_parallel": true, "self": 187809.27467475517, "children": { "steps_from_proto": { "total": 0.35520371018212415, "count": 500, "is_parallel": true, "self": 0.06166063730144167, "children": { "_process_rank_one_or_two_observation": { "total": 0.2935430728806825, "count": 2000, "is_parallel": true, "self": 0.2935430728806825 } } }, "UnityEnvironment.step": { "total": 29545.992937764546, "count": 3424690, "is_parallel": true, "self": 1575.2887994267803, "children": { "UnityEnvironment._generate_step_input": { "total": 918.4496769389986, "count": 3424690, "is_parallel": true, "self": 918.4496769389986 }, "communicator.exchange": { "total": 22536.6710482682, "count": 3424690, "is_parallel": true, "self": 22536.6710482682 }, "steps_from_proto": { "total": 4515.583413130569, "count": 6849380, "is_parallel": true, "self": 769.0175715238793, "children": { "_process_rank_one_or_two_observation": { "total": 3746.56584160669, "count": 27397520, "is_parallel": true, "self": 3746.56584160669 } } } } } } } } } } }, "trainer_advance": { "total": 173417.65788715763, "count": 3424690, "self": 365.99441912022303, "children": { "process_trajectory": { "total": 22092.0074628798, "count": 3424690, "self": 22072.849136254696, "children": { "RLTrainer._checkpoint": { "total": 19.1583266251032, "count": 100, "self": 19.1583266251032 } } }, "_update_policy": { "total": 150959.65600515762, "count": 2419, "self": 6426.084231538, "children": { "TorchPOCAOptimizer.update": { "total": 144533.57177361962, "count": 72582, "self": 144533.57177361962 } } } } } } }, "trainer_threads": { "total": 5.830079317092896e-07, "count": 1, "self": 5.830079317092896e-07 }, "TrainerController._save_models": { "total": 0.1295162909955252, "count": 1, "self": 0.007527540990849957, "children": { "RLTrainer._checkpoint": { "total": 0.12198875000467524, "count": 1, "self": 0.12198875000467524 } } } } } } }