{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 3.165266990661621, "min": 3.1445515155792236, "max": 3.2956528663635254, "count": 50 }, "SoccerTwos.Policy.Entropy.sum": { "value": 45478.5546875, "min": 43273.23046875, "max": 116318.65625, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 617.625, "min": 305.52941176470586, "max": 999.0, "count": 50 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19764.0, "min": 12716.0, "max": 28120.0, "count": 50 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1198.8048364886927, "min": 1192.7861744586792, "max": 1203.6383285599431, "count": 49 }, "SoccerTwos.Self-play.ELO.sum": { "value": 11988.048364886927, "min": 2390.382372402381, "max": 31132.04478670979, "count": 49 }, "SoccerTwos.Step.mean": { "value": 499500.0, "min": 9078.0, "max": 499500.0, "count": 50 }, "SoccerTwos.Step.sum": { "value": 499500.0, "min": 9078.0, "max": 499500.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.0029209901113063097, "min": -0.057711124420166016, "max": 0.009688904508948326, "count": 50 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -0.046735841780900955, "min": -0.9233206510543823, "max": 0.3294227421283722, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": 0.0008710850961506367, "min": -0.05763240158557892, "max": 0.010258274152874947, "count": 50 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": 0.013937361538410187, "min": -0.9221060872077942, "max": 0.3111327588558197, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.059425003826618195, "min": -0.45454545454545453, "max": 0.2604222165213691, "count": 50 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -0.9508000612258911, "min": -6.0, "max": 5.899199843406677, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.059425003826618195, "min": -0.45454545454545453, "max": 0.2604222165213691, "count": 50 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -0.9508000612258911, "min": -6.0, "max": 5.899199843406677, "count": 50 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 50 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.021989391966758014, "min": 0.021314931526042833, "max": 0.028781463496852667, "count": 23 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.021989391966758014, "min": 0.021314931526042833, "max": 0.028781463496852667, "count": 23 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.005325466050722059, "min": 7.7253093214343e-05, "max": 0.005325466050722059, "count": 23 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.005325466050722059, "min": 7.7253093214343e-05, "max": 0.005325466050722059, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.005394036829885509, "min": 7.662698961136508e-05, "max": 0.005394036829885509, "count": 23 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.005394036829885509, "min": 7.662698961136508e-05, "max": 0.005394036829885509, "count": 23 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003000000000000002, "min": 0.0003000000000000001, "max": 0.0003000000000000002, "count": 23 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003000000000000002, "min": 0.0003000000000000001, "max": 0.0003000000000000002, "count": 23 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.1999999999999999, "min": 0.1999999999999999, "max": 0.19999999999999993, "count": 23 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.1999999999999999, "min": 0.1999999999999999, "max": 0.19999999999999993, "count": 23 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 23 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 23 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1677770315", "python_version": "3.9.16 | packaged by conda-forge | (main, Feb 1 2023, 21:38:11) \n[Clang 14.0.6 ]", "command_line_arguments": "/Users/angelinux/miniforge3/envs/deep-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": "1677771041" }, "total": 726.215499, "count": 1, "self": 0.22824949899995772, "children": { "run_training.setup": { "total": 0.07520620899999919, "count": 1, "self": 0.07520620899999919 }, "TrainerController.start_learning": { "total": 725.912043292, "count": 1, "self": 0.3577547940047907, "children": { "TrainerController._reset_env": { "total": 2.336004541000035, "count": 13, "self": 2.336004541000035 }, "TrainerController.advance": { "total": 723.1292247899952, "count": 36549, "self": 0.39230298800100627, "children": { "env_step": { "total": 378.1574145819987, "count": 36549, "self": 318.1327852690006, "children": { "SubprocessEnvManager._take_step": { "total": 59.750773112001944, "count": 36549, "self": 1.8234825619938348, "children": { "TorchPolicy.evaluate": { "total": 57.92729055000811, "count": 72448, "self": 57.92729055000811 } } }, "workers": { "total": 0.27385620099615515, "count": 36549, "self": 0.0, "children": { "worker_root": { "total": 722.9064067609972, "count": 36549, "is_parallel": true, "self": 457.79318997699454, "children": { "steps_from_proto": { "total": 0.011790787999841346, "count": 26, "is_parallel": true, "self": 0.002134415999605066, "children": { "_process_rank_one_or_two_observation": { "total": 0.00965637200023628, "count": 104, "is_parallel": true, "self": 0.00965637200023628 } } }, "UnityEnvironment.step": { "total": 265.1014259960029, "count": 36549, "is_parallel": true, "self": 14.808606606005554, "children": { "UnityEnvironment._generate_step_input": { "total": 7.797140993001641, "count": 36549, "is_parallel": true, "self": 7.797140993001641 }, "communicator.exchange": { "total": 207.9217918940034, "count": 36549, "is_parallel": true, "self": 207.9217918940034 }, "steps_from_proto": { "total": 34.57388650299227, "count": 73098, "is_parallel": true, "self": 5.897746646961849, "children": { "_process_rank_one_or_two_observation": { "total": 28.676139856030424, "count": 292392, "is_parallel": true, "self": 28.676139856030424 } } } } } } } } } } }, "trainer_advance": { "total": 344.5795072199955, "count": 36549, "self": 3.398562609986527, "children": { "process_trajectory": { "total": 50.93060661000922, "count": 36549, "self": 50.81889890200918, "children": { "RLTrainer._checkpoint": { "total": 0.11170770800003993, "count": 1, "self": 0.11170770800003993 } } }, "_update_policy": { "total": 290.2503379999997, "count": 23, "self": 42.781863164000924, "children": { "TorchPOCAOptimizer.update": { "total": 247.4684748359988, "count": 1401, "self": 247.4684748359988 } } } } } } }, "trainer_threads": { "total": 3.330000026835478e-07, "count": 1, "self": 3.330000026835478e-07 }, "TrainerController._save_models": { "total": 0.08905883399995673, "count": 1, "self": 0.0007829590000483222, "children": { "RLTrainer._checkpoint": { "total": 0.08827587499990841, "count": 1, "self": 0.08827587499990841 } } } } } } }