{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.3975849151611328, "min": 1.3975849151611328, "max": 1.4284071922302246, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69508.8828125, "min": 67874.234375, "max": 77731.859375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 95.18595825426945, "min": 91.35977859778598, "max": 366.036496350365, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 50163.0, "min": 48937.0, "max": 50163.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999956.0, "min": 49895.0, "max": 1999956.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999956.0, "min": 49895.0, "max": 1999956.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3642003536224365, "min": 0.05125921964645386, "max": 2.4185760021209717, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1245.93359375, "min": 6.971253871917725, "max": 1299.4951171875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6148859314493254, "min": 1.6059245826566921, "max": 3.889459285794235, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1905.0448858737946, "min": 218.40574324131012, "max": 2031.5004369616508, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6148859314493254, "min": 1.6059245826566921, "max": 3.889459285794235, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1905.0448858737946, "min": 218.40574324131012, "max": 2031.5004369616508, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018376681891580423, "min": 0.013295681074992493, "max": 0.022223293476660425, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.036753363783160846, "min": 0.03001291224063607, "max": 0.05593564656737726, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.050557893638809526, "min": 0.020751183883597455, "max": 0.0684622330384122, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.10111578727761905, "min": 0.04150236776719491, "max": 0.2053866991152366, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.587023471024997e-06, "min": 4.587023471024997e-06, "max": 0.00029533237655587495, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.174046942049994e-06, "min": 9.174046942049994e-06, "max": 0.00084378286873905, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.101528975, "min": 0.101528975, "max": 0.198444125, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20305795, "min": 0.20305795, "max": 0.5812609499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.629585249999997e-05, "min": 8.629585249999997e-05, "max": 0.0049223618375, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00017259170499999994, "min": 0.00017259170499999994, "max": 0.014064921405000003, "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": "1712404993", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1712407662" }, "total": 2668.379221491, "count": 1, "self": 0.8064067400000567, "children": { "run_training.setup": { "total": 0.10675024400001121, "count": 1, "self": 0.10675024400001121 }, "TrainerController.start_learning": { "total": 2667.466064507, "count": 1, "self": 5.067278052023994, "children": { "TrainerController._reset_env": { "total": 3.656751364999991, "count": 1, "self": 3.656751364999991 }, "TrainerController.advance": { "total": 2658.553113895976, "count": 231463, "self": 5.22535163304201, "children": { "env_step": { "total": 2138.5558347299593, "count": 231463, "self": 1769.7513491140353, "children": { "SubprocessEnvManager._take_step": { "total": 365.3601539528461, "count": 231463, "self": 19.1639386628799, "children": { "TorchPolicy.evaluate": { "total": 346.1962152899662, "count": 222921, "self": 346.1962152899662 } } }, "workers": { "total": 3.444331663078003, "count": 231463, "self": 0.0, "children": { "worker_root": { "total": 2659.1314239430967, "count": 231463, "is_parallel": true, "self": 1237.9036136301918, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001125971999954345, "count": 1, "is_parallel": true, "self": 0.0003014989999883255, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008244729999660194, "count": 2, "is_parallel": true, "self": 0.0008244729999660194 } } }, "UnityEnvironment.step": { "total": 0.03163817500001187, "count": 1, "is_parallel": true, "self": 0.00042371699998966506, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00024449599999343263, "count": 1, "is_parallel": true, "self": 0.00024449599999343263 }, "communicator.exchange": { "total": 0.030157830999996804, "count": 1, "is_parallel": true, "self": 0.030157830999996804 }, "steps_from_proto": { "total": 0.0008121310000319681, "count": 1, "is_parallel": true, "self": 0.00021024100004751745, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006018899999844507, "count": 2, "is_parallel": true, "self": 0.0006018899999844507 } } } } } } }, "UnityEnvironment.step": { "total": 1421.227810312905, "count": 231462, "is_parallel": true, "self": 43.71402651797666, "children": { "UnityEnvironment._generate_step_input": { "total": 90.6062976921063, "count": 231462, "is_parallel": true, "self": 90.6062976921063 }, "communicator.exchange": { "total": 1184.223601187894, "count": 231462, "is_parallel": true, "self": 1184.223601187894 }, "steps_from_proto": { "total": 102.68388491492794, "count": 231462, "is_parallel": true, "self": 36.39666165193796, "children": { "_process_rank_one_or_two_observation": { "total": 66.28722326298998, "count": 462924, "is_parallel": true, "self": 66.28722326298998 } } } } } } } } } } }, "trainer_advance": { "total": 514.7719275329744, "count": 231463, "self": 7.660827995975978, "children": { "process_trajectory": { "total": 159.72329204999858, "count": 231463, "self": 158.12651345299787, "children": { "RLTrainer._checkpoint": { "total": 1.5967785970007071, "count": 10, "self": 1.5967785970007071 } } }, "_update_policy": { "total": 347.3878074869998, "count": 96, "self": 279.50120211500183, "children": { "TorchPPOOptimizer.update": { "total": 67.88660537199797, "count": 2880, "self": 67.88660537199797 } } } } } } }, "trainer_threads": { "total": 1.1550000635907054e-06, "count": 1, "self": 1.1550000635907054e-06 }, "TrainerController._save_models": { "total": 0.18892003900009513, "count": 1, "self": 0.003052208000099199, "children": { "RLTrainer._checkpoint": { "total": 0.18586783099999593, "count": 1, "self": 0.18586783099999593 } } } } } } }