{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.409610390663147, "min": 1.409610390663147, "max": 1.4280730485916138, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71520.8125, "min": 67335.1015625, "max": 79387.6796875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 77.56132075471699, "min": 72.62941176470588, "max": 401.664, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49329.0, "min": 49184.0, "max": 50208.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999354.0, "min": 49925.0, "max": 1999354.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999354.0, "min": 49925.0, "max": 1999354.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.496853828430176, "min": 0.03379891440272331, "max": 2.539558172225952, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1587.9990234375, "min": 4.191065311431885, "max": 1697.203857421875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.862816942375411, "min": 1.8494302404503669, "max": 4.110313229162145, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2456.7515753507614, "min": 229.3293498158455, "max": 2638.940443634987, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.862816942375411, "min": 1.8494302404503669, "max": 4.110313229162145, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2456.7515753507614, "min": 229.3293498158455, "max": 2638.940443634987, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015959290935703998, "min": 0.013049049405769134, "max": 0.019401211686393555, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.047877872807112, "min": 0.026098098811538267, "max": 0.0539448166033253, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05939422017998166, "min": 0.022956109046936034, "max": 0.06541855533917745, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17818266053994497, "min": 0.04591221809387207, "max": 0.1804283561805884, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.886048704683326e-06, "min": 3.886048704683326e-06, "max": 0.000295298626567125, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.165814611404998e-05, "min": 1.165814611404998e-05, "max": 0.0008440194186601999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10129531666666665, "min": 0.10129531666666665, "max": 0.198432875, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30388594999999996, "min": 0.20774964999999995, "max": 0.5813398000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.463630166666656e-05, "min": 7.463630166666656e-05, "max": 0.004921800462500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002239089049999997, "min": 0.0002239089049999997, "max": 0.014068856019999996, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1684809647", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --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": "1684812254" }, "total": 2606.850854997, "count": 1, "self": 0.6887266220001038, "children": { "run_training.setup": { "total": 0.043528120000019044, "count": 1, "self": 0.043528120000019044 }, "TrainerController.start_learning": { "total": 2606.1186002550003, "count": 1, "self": 4.68189115497762, "children": { "TrainerController._reset_env": { "total": 3.845989283999984, "count": 1, "self": 3.845989283999984 }, "TrainerController.advance": { "total": 2597.403472578022, "count": 233235, "self": 4.911101999014136, "children": { "env_step": { "total": 2015.6473194920745, "count": 233235, "self": 1702.6344406281519, "children": { "SubprocessEnvManager._take_step": { "total": 309.91139758301244, "count": 233235, "self": 17.985924515950614, "children": { "TorchPolicy.evaluate": { "total": 291.92547306706183, "count": 222960, "self": 291.92547306706183 } } }, "workers": { "total": 3.101481280910093, "count": 233235, "self": 0.0, "children": { "worker_root": { "total": 2597.6923008359536, "count": 233235, "is_parallel": true, "self": 1207.3522220978684, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009967660000143042, "count": 1, "is_parallel": true, "self": 0.0003074620000234063, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006893039999908979, "count": 2, "is_parallel": true, "self": 0.0006893039999908979 } } }, "UnityEnvironment.step": { "total": 0.03239168900000777, "count": 1, "is_parallel": true, "self": 0.000365316999989318, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00025216000000227723, "count": 1, "is_parallel": true, "self": 0.00025216000000227723 }, "communicator.exchange": { "total": 0.03081106400003364, "count": 1, "is_parallel": true, "self": 0.03081106400003364 }, "steps_from_proto": { "total": 0.0009631479999825387, "count": 1, "is_parallel": true, "self": 0.00044119599999703496, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005219519999855038, "count": 2, "is_parallel": true, "self": 0.0005219519999855038 } } } } } } }, "UnityEnvironment.step": { "total": 1390.3400787380851, "count": 233234, "is_parallel": true, "self": 40.413624601033234, "children": { "UnityEnvironment._generate_step_input": { "total": 86.96863044412629, "count": 233234, "is_parallel": true, "self": 86.96863044412629 }, "communicator.exchange": { "total": 1163.378440351976, "count": 233234, "is_parallel": true, "self": 1163.378440351976 }, "steps_from_proto": { "total": 99.57938334094956, "count": 233234, "is_parallel": true, "self": 38.99854334582011, "children": { "_process_rank_one_or_two_observation": { "total": 60.58083999512945, "count": 466468, "is_parallel": true, "self": 60.58083999512945 } } } } } } } } } } }, "trainer_advance": { "total": 576.8450510869334, "count": 233235, "self": 7.345129478974741, "children": { "process_trajectory": { "total": 151.2630160799584, "count": 233235, "self": 149.98852726695867, "children": { "RLTrainer._checkpoint": { "total": 1.2744888129997207, "count": 10, "self": 1.2744888129997207 } } }, "_update_policy": { "total": 418.2369055280003, "count": 97, "self": 356.8001829979936, "children": { "TorchPPOOptimizer.update": { "total": 61.436722530006705, "count": 2910, "self": 61.436722530006705 } } } } } } }, "trainer_threads": { "total": 1.4770002962904982e-06, "count": 1, "self": 1.4770002962904982e-06 }, "TrainerController._save_models": { "total": 0.18724576100021295, "count": 1, "self": 0.0027617800001280557, "children": { "RLTrainer._checkpoint": { "total": 0.1844839810000849, "count": 1, "self": 0.1844839810000849 } } } } } } }