{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.8800697326660156, "min": 2.7971508502960205, "max": 3.2957067489624023, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 49214.6328125, "min": 11543.6328125, "max": 132192.15625, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 197.92592592592592, "min": 115.02564102564102, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 21376.0, "min": 16132.0, "max": 23648.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1272.36506910111, "min": 1194.692912581449, "max": 1272.36506910111, "count": 358 }, "SoccerTwos.Self-play.ELO.sum": { "value": 68707.71373145994, "min": 2389.458277317844, "max": 97962.82461127103, "count": 358 }, "SoccerTwos.Step.mean": { "value": 4999508.0, "min": 9976.0, "max": 4999508.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999508.0, "min": 9976.0, "max": 4999508.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.08261680603027344, "min": -0.02772657200694084, "max": 0.08261680603027344, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 4.461307525634766, "min": -0.3755653500556946, "max": 4.461307525634766, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.09392579644918442, "min": -0.019030623137950897, "max": 0.09392579644918442, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 5.071992874145508, "min": -0.39550870656967163, "max": 5.071992874145508, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": 0.020985184513308382, "min": -0.6199400007724762, "max": 0.44327059563468485, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 1.1331999637186527, "min": -15.8471999168396, "max": 18.599999964237213, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.020985184513308382, "min": -0.6199400007724762, "max": 0.44327059563468485, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 1.1331999637186527, "min": -15.8471999168396, "max": 18.599999964237213, "count": 500 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 500 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.01645166991026296, "min": 0.010685314397172381, "max": 0.025194068586764238, "count": 233 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.01645166991026296, "min": 0.010685314397172381, "max": 0.025194068586764238, "count": 233 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.04083418982724349, "min": 1.8388129466491894e-07, "max": 0.04083418982724349, "count": 233 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.04083418982724349, "min": 1.8388129466491894e-07, "max": 0.04083418982724349, "count": 233 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.04173363422354062, "min": 1.941327316975124e-07, "max": 0.04173363422354062, "count": 233 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.04173363422354062, "min": 1.941327316975124e-07, "max": 0.04173363422354062, "count": 233 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 233 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 233 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 233 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 233 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 233 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 233 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678803189", "python_version": "3.9.16 (main, Mar 8 2023, 04:29:44) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/Ca/opt/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics", "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": "1678823876" }, "total": 20686.559014875, "count": 1, "self": 0.673993167001754, "children": { "run_training.setup": { "total": 0.329239458, "count": 1, "self": 0.329239458 }, "TrainerController.start_learning": { "total": 20685.55578225, "count": 1, "self": 4.179235140993114, "children": { "TrainerController._reset_env": { "total": 8.37700170799874, "count": 25, "self": 8.37700170799874 }, "TrainerController.advance": { "total": 20672.89009298401, "count": 325185, "self": 4.0852370792672446, "children": { "env_step": { "total": 4611.209081970977, "count": 325185, "self": 3748.059476784651, "children": { "SubprocessEnvManager._take_step": { "total": 860.3115061578112, "count": 325185, "self": 22.73343601277213, "children": { "TorchPolicy.evaluate": { "total": 837.5780701450391, "count": 645002, "self": 837.5780701450391 } } }, "workers": { "total": 2.8380990285152663, "count": 325185, "self": 0.0, "children": { "worker_root": { "total": 20671.292230147857, "count": 325185, "is_parallel": true, "self": 17455.679545158306, "children": { "steps_from_proto": { "total": 0.03426083300603011, "count": 50, "is_parallel": true, "self": 0.0059753719907442715, "children": { "_process_rank_one_or_two_observation": { "total": 0.02828546101528584, "count": 200, "is_parallel": true, "self": 0.02828546101528584 } } }, "UnityEnvironment.step": { "total": 3215.578424156547, "count": 325185, "is_parallel": true, "self": 138.84121177521865, "children": { "UnityEnvironment._generate_step_input": { "total": 92.73925554655374, "count": 325185, "is_parallel": true, "self": 92.73925554655374 }, "communicator.exchange": { "total": 2554.985181854378, "count": 325185, "is_parallel": true, "self": 2554.985181854378 }, "steps_from_proto": { "total": 429.0127749803968, "count": 650370, "is_parallel": true, "self": 69.99788359482523, "children": { "_process_rank_one_or_two_observation": { "total": 359.01489138557156, "count": 2601480, "is_parallel": true, "self": 359.01489138557156 } } } } } } } } } } }, "trainer_advance": { "total": 16057.595773933765, "count": 325185, "self": 34.39603538314623, "children": { "process_trajectory": { "total": 1798.6496443966257, "count": 325185, "self": 1797.5627657706264, "children": { "RLTrainer._checkpoint": { "total": 1.0868786259993612, "count": 10, "self": 1.0868786259993612 } } }, "_update_policy": { "total": 14224.550094153992, "count": 233, "self": 610.1583948359221, "children": { "TorchPOCAOptimizer.update": { "total": 13614.39169931807, "count": 6990, "self": 13614.39169931807 } } } } } } }, "trainer_threads": { "total": 5.000001692678779e-07, "count": 1, "self": 5.000001692678779e-07 }, "TrainerController._save_models": { "total": 0.10945191700011492, "count": 1, "self": 0.0009360839976579882, "children": { "RLTrainer._checkpoint": { "total": 0.10851583300245693, "count": 1, "self": 0.10851583300245693 } } } } } } }