{ "name": "root", "gauges": { "SoccerTwos.Policy.Entropy.mean": { "value": 2.0744967460632324, "min": 2.061256170272827, "max": 3.2956643104553223, "count": 472 }, "SoccerTwos.Policy.Entropy.sum": { "value": 43547.8359375, "min": 16979.185546875, "max": 161875.40625, "count": 472 }, "SoccerTwos.Environment.EpisodeLength.mean": { "value": 65.53333333333333, "min": 44.477064220183486, "max": 999.0, "count": 472 }, "SoccerTwos.Environment.EpisodeLength.sum": { "value": 19660.0, "min": 16120.0, "max": 23756.0, "count": 472 }, "SoccerTwos.Self-play.ELO.mean": { "value": 1528.1564812993056, "min": 1194.160898636277, "max": 1554.9791073077633, "count": 453 }, "SoccerTwos.Self-play.ELO.sum": { "value": 229223.47219489585, "min": 2388.321797272554, "max": 331253.87356936734, "count": 453 }, "SoccerTwos.Step.mean": { "value": 4719898.0, "min": 9942.0, "max": 4719898.0, "count": 472 }, "SoccerTwos.Step.sum": { "value": 4719898.0, "min": 9942.0, "max": 4719898.0, "count": 472 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": { "value": -0.01887659728527069, "min": -0.10542313754558563, "max": 0.14932888746261597, "count": 472 }, "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": { "value": -2.8314895629882812, "min": -14.300395965576172, "max": 20.86272430419922, "count": 472 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": { "value": -0.021288074553012848, "min": -0.10537904500961304, "max": 0.14755292236804962, "count": 472 }, "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": { "value": -3.193211078643799, "min": -13.963614463806152, "max": 20.708911895751953, "count": 472 }, "SoccerTwos.Environment.CumulativeReward.mean": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 472 }, "SoccerTwos.Environment.CumulativeReward.sum": { "value": 0.0, "min": 0.0, "max": 0.0, "count": 472 }, "SoccerTwos.Policy.ExtrinsicReward.mean": { "value": -0.13239599903424581, "min": -0.625, "max": 0.49411763952058907, "count": 472 }, "SoccerTwos.Policy.ExtrinsicReward.sum": { "value": -19.85939985513687, "min": -41.071800231933594, "max": 51.71139979362488, "count": 472 }, "SoccerTwos.Environment.GroupCumulativeReward.mean": { "value": -0.13239599903424581, "min": -0.625, "max": 0.49411763952058907, "count": 472 }, "SoccerTwos.Environment.GroupCumulativeReward.sum": { "value": -19.85939985513687, "min": -41.071800231933594, "max": 51.71139979362488, "count": 472 }, "SoccerTwos.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 472 }, "SoccerTwos.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 472 }, "SoccerTwos.Losses.PolicyLoss.mean": { "value": 0.016272481051661694, "min": 0.010424615769200804, "max": 0.023758423148440972, "count": 225 }, "SoccerTwos.Losses.PolicyLoss.sum": { "value": 0.016272481051661694, "min": 0.010424615769200804, "max": 0.023758423148440972, "count": 225 }, "SoccerTwos.Losses.ValueLoss.mean": { "value": 0.10069958294431368, "min": 3.700576038075572e-06, "max": 0.11594027852018675, "count": 225 }, "SoccerTwos.Losses.ValueLoss.sum": { "value": 0.10069958294431368, "min": 3.700576038075572e-06, "max": 0.11594027852018675, "count": 225 }, "SoccerTwos.Losses.BaselineLoss.mean": { "value": 0.10207154403130213, "min": 3.6573177377855853e-06, "max": 0.11809751565257708, "count": 225 }, "SoccerTwos.Losses.BaselineLoss.sum": { "value": 0.10207154403130213, "min": 3.6573177377855853e-06, "max": 0.11809751565257708, "count": 225 }, "SoccerTwos.Policy.LearningRate.mean": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 225 }, "SoccerTwos.Policy.LearningRate.sum": { "value": 0.0003, "min": 0.0003, "max": 0.0003, "count": 225 }, "SoccerTwos.Policy.Epsilon.mean": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 225 }, "SoccerTwos.Policy.Epsilon.sum": { "value": 0.20000000000000007, "min": 0.20000000000000007, "max": 0.20000000000000007, "count": 225 }, "SoccerTwos.Policy.Beta.mean": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 225 }, "SoccerTwos.Policy.Beta.sum": { "value": 0.005000000000000001, "min": 0.005000000000000001, "max": 0.005000000000000001, "count": 225 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687879263", "python_version": "3.9.16 (main, May 15 2023, 23:46:34) \n[GCC 11.2.0]", "command_line_arguments": "/home/rcls/APPs/anaconda3/envs/rl/bin/mlagents-learn config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos2 --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+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1687895159" }, "total": 15896.488707362005, "count": 1, "self": 0.5369108009908814, "children": { "run_training.setup": { "total": 0.00820854600169696, "count": 1, "self": 0.00820854600169696 }, "TrainerController.start_learning": { "total": 15895.943588015012, "count": 1, "self": 7.708126039680792, "children": { "TrainerController._reset_env": { "total": 1.5737629419600125, "count": 24, "self": 1.5737629419600125 }, "TrainerController.advance": { "total": 15886.47150302236, "count": 317886, "self": 8.081340691103833, "children": { "env_step": { "total": 5974.421085315058, "count": 317886, "self": 4905.711345372896, "children": { "SubprocessEnvManager._take_step": { "total": 1063.8875759330112, "count": 317886, "self": 43.56820851439261, "children": { "TorchPolicy.evaluate": { "total": 1020.3193674186186, "count": 598670, "self": 1020.3193674186186 } } }, "workers": { "total": 4.822164009150583, "count": 317886, "self": 0.0, "children": { "worker_root": { "total": 15881.829722142284, "count": 317886, "is_parallel": true, "self": 11838.092291657493, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0016371259989682585, "count": 2, "is_parallel": true, "self": 0.0003801429702434689, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012569830287247896, "count": 8, "is_parallel": true, "self": 0.0012569830287247896 } } }, "UnityEnvironment.step": { "total": 0.01787375900312327, "count": 1, "is_parallel": true, "self": 0.0004416879964992404, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041525199776515365, "count": 1, "is_parallel": true, "self": 0.00041525199776515365 }, "communicator.exchange": { "total": 0.01568464099545963, "count": 1, "is_parallel": true, "self": 0.01568464099545963 }, "steps_from_proto": { "total": 0.0013321780133992434, "count": 2, "is_parallel": true, "self": 0.0003262840327806771, "children": { "_process_rank_one_or_two_observation": { "total": 0.0010058939806185663, "count": 8, "is_parallel": true, "self": 0.0010058939806185663 } } } } } } }, "UnityEnvironment.step": { "total": 4043.68896008085, "count": 317885, "is_parallel": true, "self": 240.81878162530484, "children": { "UnityEnvironment._generate_step_input": { "total": 168.6598716371518, "count": 317885, "is_parallel": true, "self": 168.6598716371518 }, "communicator.exchange": { "total": 2913.374164572335, "count": 317885, "is_parallel": true, "self": 2913.374164572335 }, "steps_from_proto": { "total": 720.8361422460584, "count": 635770, "is_parallel": true, "self": 140.4202986920136, "children": { "_process_rank_one_or_two_observation": { "total": 580.4158435540448, "count": 2543080, "is_parallel": true, "self": 580.4158435540448 } } } } }, "steps_from_proto": { "total": 0.048470403940882534, "count": 46, "is_parallel": true, "self": 0.00948453787714243, "children": { "_process_rank_one_or_two_observation": { "total": 0.038985866063740104, "count": 184, "is_parallel": true, "self": 0.038985866063740104 } } } } } } } } }, "trainer_advance": { "total": 9903.969077016198, "count": 317885, "self": 53.17670554446522, "children": { "process_trajectory": { "total": 1060.648966794659, "count": 317885, "self": 1058.7333575366356, "children": { "RLTrainer._checkpoint": { "total": 1.9156092580233235, "count": 9, "self": 1.9156092580233235 } } }, "_update_policy": { "total": 8790.143404677074, "count": 225, "self": 712.2272357027396, "children": { "TorchPOCAOptimizer.update": { "total": 8077.916168974334, "count": 6750, "self": 8077.916168974334 } } } } } } }, "trainer_threads": { "total": 1.7700076568871737e-06, "count": 1, "self": 1.7700076568871737e-06 }, "TrainerController._save_models": { "total": 0.19019424100406468, "count": 1, "self": 0.002219676011009142, "children": { "RLTrainer._checkpoint": { "total": 0.18797456499305554, "count": 1, "self": 0.18797456499305554 } } } } } } }