{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4080817699432373, "min": 1.4080817699432373, "max": 1.4284272193908691, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69135.40625, "min": 69135.40625, "max": 76588.6953125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 81.825, "min": 76.90795631825273, "max": 387.9612403100775, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49095.0, "min": 48949.0, "max": 50047.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999929.0, "min": 49726.0, "max": 1999929.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999929.0, "min": 49726.0, "max": 1999929.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4922502040863037, "min": -0.04601811617612839, "max": 2.531200885772705, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1495.35009765625, "min": -5.890318870544434, "max": 1604.283447265625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8384710224469503, "min": 1.8016590096522123, "max": 4.069016265568613, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2303.08261346817, "min": 230.61235323548317, "max": 2530.333663582802, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8384710224469503, "min": 1.8016590096522123, "max": 4.069016265568613, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2303.08261346817, "min": 230.61235323548317, "max": 2530.333663582802, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015933995858490056, "min": 0.013357469670881982, "max": 0.01982119088570471, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04780198757547017, "min": 0.026714939341763964, "max": 0.0575841957819648, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05939134438004758, "min": 0.02463892937327425, "max": 0.06555458419024945, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17817403314014274, "min": 0.0492778587465485, "max": 0.1799254688123862, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.865248711616672e-06, "min": 3.865248711616672e-06, "max": 0.00029532450155849994, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1595746134850018e-05, "min": 1.1595746134850018e-05, "max": 0.0008441569686143498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1012883833333333, "min": 0.1012883833333333, "max": 0.19844150000000008, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3038651499999999, "min": 0.20771615, "max": 0.5813856500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.429032833333343e-05, "min": 7.429032833333343e-05, "max": 0.004922230849999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022287098500000028, "min": 0.00022287098500000028, "max": 0.014071143934999999, "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": "1671614892", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1671617081" }, "total": 2188.920948209, "count": 1, "self": 0.4008911689998058, "children": { "run_training.setup": { "total": 0.10783353600004375, "count": 1, "self": 0.10783353600004375 }, "TrainerController.start_learning": { "total": 2188.412223504, "count": 1, "self": 3.715478545092992, "children": { "TrainerController._reset_env": { "total": 7.976220884999975, "count": 1, "self": 7.976220884999975 }, "TrainerController.advance": { "total": 2176.605155660907, "count": 233191, "self": 4.080405764891566, "children": { "env_step": { "total": 1703.5246587300157, "count": 233191, "self": 1436.3459107131198, "children": { "SubprocessEnvManager._take_step": { "total": 264.7098513860948, "count": 233191, "self": 13.983400070135303, "children": { "TorchPolicy.evaluate": { "total": 250.72645131595948, "count": 222966, "self": 62.71689189699623, "children": { "TorchPolicy.sample_actions": { "total": 188.00955941896325, "count": 222966, "self": 188.00955941896325 } } } } }, "workers": { "total": 2.468896630801055, "count": 233191, "self": 0.0, "children": { "worker_root": { "total": 2180.5615284477735, "count": 233191, "is_parallel": true, "self": 996.6386857247567, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021719050000683637, "count": 1, "is_parallel": true, "self": 0.00031311600002936757, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018587890000389962, "count": 2, "is_parallel": true, "self": 0.0018587890000389962 } } }, "UnityEnvironment.step": { "total": 0.026376110999990487, "count": 1, "is_parallel": true, "self": 0.00027928099996188394, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001773129999946832, "count": 1, "is_parallel": true, "self": 0.0001773129999946832 }, "communicator.exchange": { "total": 0.025174415000037698, "count": 1, "is_parallel": true, "self": 0.025174415000037698 }, "steps_from_proto": { "total": 0.0007451019999962227, "count": 1, "is_parallel": true, "self": 0.00023701699990397174, "children": { "_process_rank_one_or_two_observation": { "total": 0.000508085000092251, "count": 2, "is_parallel": true, "self": 0.000508085000092251 } } } } } } }, "UnityEnvironment.step": { "total": 1183.9228427230169, "count": 233190, "is_parallel": true, "self": 34.196790766259255, "children": { "UnityEnvironment._generate_step_input": { "total": 74.87435808492728, "count": 233190, "is_parallel": true, "self": 74.87435808492728 }, "communicator.exchange": { "total": 984.0718693798867, "count": 233190, "is_parallel": true, "self": 984.0718693798867 }, "steps_from_proto": { "total": 90.7798244919436, "count": 233190, "is_parallel": true, "self": 37.11595759407919, "children": { "_process_rank_one_or_two_observation": { "total": 53.66386689786441, "count": 466380, "is_parallel": true, "self": 53.66386689786441 } } } } } } } } } } }, "trainer_advance": { "total": 469.0000911659995, "count": 233191, "self": 5.897698248082293, "children": { "process_trajectory": { "total": 149.8470864059177, "count": 233191, "self": 148.69645839291798, "children": { "RLTrainer._checkpoint": { "total": 1.1506280129997322, "count": 10, "self": 1.1506280129997322 } } }, "_update_policy": { "total": 313.2553065119995, "count": 97, "self": 260.47667216199204, "children": { "TorchPPOOptimizer.update": { "total": 52.77863435000745, "count": 2910, "self": 52.77863435000745 } } } } } } }, "trainer_threads": { "total": 7.160001587180886e-07, "count": 1, "self": 7.160001587180886e-07 }, "TrainerController._save_models": { "total": 0.11536769699978322, "count": 1, "self": 0.0018828279994522745, "children": { "RLTrainer._checkpoint": { "total": 0.11348486900033095, "count": 1, "self": 0.11348486900033095 } } } } } } }