{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 1.8047733306884766, "min": 1.7506589889526367, "max": 3.295727014541626, "count": 500 }, "SoccerTwos.Policy.Entropy.sum": { "value": 35460.1875, "min": 8425.765625, "max": 124395.3203125, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 55.422222222222224, "min": 39.40163934426229, "max": 999.0, "count": 500 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19952.0, "min": 13760.0, "max": 26996.0, "count": 500 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1516.310564185642, "min": 1168.318664004272, "max": 1527.451665508708, "count": 488 }, "SoccerTwos.Self-play.ELO.sum": { "value": 272935.9015534156, "min": 2347.167035007367, "max": 367197.7689797528, "count": 488 }, "SoccerTwos.Step.mean": { "value": 4999998.0, "min": 9514.0, "max": 4999998.0, "count": 500 }, "SoccerTwos.Step.sum": { "value": 4999998.0, "min": 9514.0, "max": 4999998.0, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": 0.02635500766336918, "min": -0.1327667534351349, "max": 0.2048211395740509, "count": 500 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": 4.717546463012695, "min": -28.279319763183594, "max": 27.99909782409668, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.027237825095653534, "min": -0.12753306329250336, "max": 0.1981039047241211, "count": 500 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 4.875570774078369, "min": -27.16454315185547, "max": 27.693038940429688, "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": 0.06397765175590302, "min": -0.6024666693475511, "max": 0.5980133334795634, "count": 500 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": 11.45199966430664, "min": -51.776400208473206, "max": 58.15599989891052, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": 0.06397765175590302, "min": -0.6024666693475511, "max": 0.5980133334795634, "count": 500 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": 11.45199966430664, "min": -51.776400208473206, "max": 58.15599989891052, "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": 0.017978125326529457, "min": 0.011096322290541138, "max": 0.02351805433475723, "count": 239 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.017978125326529457, "min": 0.011096322290541138, "max": 0.02351805433475723, "count": 239 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.09817635715007782, "min": 5.527079315470473e-06, "max": 0.12303231035669644, "count": 239 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.09817635715007782, "min": 5.527079315470473e-06, "max": 0.12303231035669644, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.09932974750796954, "min": 5.59982440033006e-06, "max": 0.12475675294796626, "count": 239 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.09932974750796954, "min": 5.59982440033006e-06, "max": 0.12475675294796626, "count": 239 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 239 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000004, "max": 0.20000000000000007, "count": 239 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 239 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 239 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1691422565", "python_version": "3.9.7 (default, Sep 16 2021, 23:53:23) \n[Clang 12.0.0 ]", "command_line_arguments": "/Users/mrmrob003/opt/anaconda3/envs/unity-mla/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": "1691440898" }, "total": 18332.000263458, "count": 1, "self": 0.1878028329992958, "children": { "run_training.setup": { "total": 0.19681766700000003, "count": 1, "self": 0.19681766700000003 }, "TrainerController.start_learning": { "total": 18331.615642958, "count": 1, "self": 3.9310907929866516, "children": { "TrainerController._reset_env": { "total": 3.0180379999964924, "count": 25, "self": 3.0180379999964924 }, "TrainerController.advance": { "total": 18324.58613587402, "count": 340417, "self": 3.479135186655185, "children": { "env_step": { "total": 14339.037296880457, "count": 340417, "self": 13767.449292414245, "children": { "SubprocessEnvManager._take_step": { "total": 568.9161772708578, "count": 340417, "self": 16.83921516515784, "children": { "TorchPolicy.evaluate": { "total": 552.0769621057, "count": 632194, "self": 552.0769621057 } } }, "workers": { "total": 2.6718271953536052, "count": 340417, "self": 0.0, "children": { "worker_root": { "total": 18323.663271818627, "count": 340417, "is_parallel": true, "self": 5070.847689271004, "children": { "steps_from_proto": { "total": 0.03189658199895229, "count": 50, "is_parallel": true, "self": 0.004472072001107552, "children": { "_process_rank_one_or_two_observation": { "total": 0.027424509997844737, "count": 200, "is_parallel": true, "self": 0.027424509997844737 } } }, "UnityEnvironment.step": { "total": 13252.783685965624, "count": 340417, "is_parallel": true, "self": 37.03243819452473, "children": { "UnityEnvironment._generate_step_input": { "total": 215.91403868248227, "count": 340417, "is_parallel": true, "self": 215.91403868248227 }, "communicator.exchange": { "total": 12568.909338877527, "count": 340417, "is_parallel": true, "self": 12568.909338877527 }, "steps_from_proto": { "total": 430.9278702110893, "count": 680834, "is_parallel": true, "self": 59.581732542039504, "children": { "_process_rank_one_or_two_observation": { "total": 371.3461376690498, "count": 2723336, "is_parallel": true, "self": 371.3461376690498 } } } } } } } } } } }, "trainer_advance": { "total": 3982.069703806905, "count": 340417, "self": 28.569206865402066, "children": { "process_trajectory": { "total": 817.1338541785244, "count": 340417, "self": 816.2785569285263, "children": { "RLTrainer._checkpoint": { "total": 0.8552972499981024, "count": 10, "self": 0.8552972499981024 } } }, "_update_policy": { "total": 3136.3666427629787, "count": 239, "self": 424.7424057310136, "children": { "TorchPOCAOptimizer.update": { "total": 2711.624237031965, "count": 7179, "self": 2711.624237031965 } } } } } } }, "trainer_threads": { "total": 3.749992174562067e-07, "count": 1, "self": 3.749992174562067e-07 }, "TrainerController._save_models": { "total": 0.08037791600145283, "count": 1, "self": 0.0013051240021013655, "children": { "RLTrainer._checkpoint": { "total": 0.07907279199935147, "count": 1, "self": 0.07907279199935147 } } } } } } }