{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4036035537719727, "min": 1.4036035537719727, "max": 1.4270000457763672, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69868.578125, "min": 68991.34375, "max": 77886.6875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 112.28473804100227, "min": 82.79899497487438, "max": 388.8139534883721, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49293.0, "min": 49027.0, "max": 50157.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999995.0, "min": 49959.0, "max": 1999995.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999995.0, "min": 49959.0, "max": 1999995.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.312316417694092, "min": 0.20509867370128632, "max": 2.4191551208496094, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1015.1068725585938, "min": 26.25263023376465, "max": 1399.408203125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.471151205428912, "min": 1.838357611646643, "max": 3.890292937992609, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1523.8353791832924, "min": 235.3097742907703, "max": 2186.920107781887, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.471151205428912, "min": 1.838357611646643, "max": 3.890292937992609, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1523.8353791832924, "min": 235.3097742907703, "max": 2186.920107781887, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.014595517161392813, "min": 0.012302168877552807, "max": 0.01924153425473681, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04378655148417844, "min": 0.024604337755105614, "max": 0.05730619498838981, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.046745044696662165, "min": 0.020302615594118834, "max": 0.05958426383634409, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1402351340899865, "min": 0.04060523118823767, "max": 0.1691768191754818, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.393698868799997e-06, "min": 3.393698868799997e-06, "max": 0.000295308976563675, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0181096606399991e-05, "min": 1.0181096606399991e-05, "max": 0.0008440671186442999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10113119999999999, "min": 0.10113119999999999, "max": 0.19843632499999997, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3033936, "min": 0.20744025, "max": 0.5813556999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.644687999999995e-05, "min": 6.644687999999995e-05, "max": 0.004921972617500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019934063999999985, "min": 0.00019934063999999985, "max": 0.01406964943, "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": "1670793933", "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": "1670796102" }, "total": 2168.670300396, "count": 1, "self": 0.38453834099982487, "children": { "run_training.setup": { "total": 0.10602859100004025, "count": 1, "self": 0.10602859100004025 }, "TrainerController.start_learning": { "total": 2168.179733464, "count": 1, "self": 3.7773962719420524, "children": { "TrainerController._reset_env": { "total": 9.296338531000004, "count": 1, "self": 9.296338531000004 }, "TrainerController.advance": { "total": 2154.9943098700583, "count": 232061, "self": 3.981401118992835, "children": { "env_step": { "total": 1688.8927048600247, "count": 232061, "self": 1419.8360696589311, "children": { "SubprocessEnvManager._take_step": { "total": 266.4632668580572, "count": 232061, "self": 14.159029884015126, "children": { "TorchPolicy.evaluate": { "total": 252.30423697404206, "count": 223013, "self": 63.14683654204316, "children": { "TorchPolicy.sample_actions": { "total": 189.1574004319989, "count": 223013, "self": 189.1574004319989 } } } } }, "workers": { "total": 2.5933683430363317, "count": 232061, "self": 0.0, "children": { "worker_root": { "total": 2160.5869151449688, "count": 232061, "is_parallel": true, "self": 994.7031146410229, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0019990810000081183, "count": 1, "is_parallel": true, "self": 0.0003405660000339594, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016585149999741589, "count": 2, "is_parallel": true, "self": 0.0016585149999741589 } } }, "UnityEnvironment.step": { "total": 0.03809210399998619, "count": 1, "is_parallel": true, "self": 0.0003476809999369834, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018370399999412257, "count": 1, "is_parallel": true, "self": 0.00018370399999412257 }, "communicator.exchange": { "total": 0.03685773300003348, "count": 1, "is_parallel": true, "self": 0.03685773300003348 }, "steps_from_proto": { "total": 0.0007029860000216104, "count": 1, "is_parallel": true, "self": 0.00023191499997210485, "children": { "_process_rank_one_or_two_observation": { "total": 0.00047107100004950553, "count": 2, "is_parallel": true, "self": 0.00047107100004950553 } } } } } } }, "UnityEnvironment.step": { "total": 1165.8838005039458, "count": 232060, "is_parallel": true, "self": 34.37506789002555, "children": { "UnityEnvironment._generate_step_input": { "total": 74.21281026905865, "count": 232060, "is_parallel": true, "self": 74.21281026905865 }, "communicator.exchange": { "total": 966.3394162629079, "count": 232060, "is_parallel": true, "self": 966.3394162629079 }, "steps_from_proto": { "total": 90.95650608195393, "count": 232060, "is_parallel": true, "self": 37.06291720984319, "children": { "_process_rank_one_or_two_observation": { "total": 53.89358887211074, "count": 464120, "is_parallel": true, "self": 53.89358887211074 } } } } } } } } } } }, "trainer_advance": { "total": 462.1202038910406, "count": 232061, "self": 6.531912432091872, "children": { "process_trajectory": { "total": 142.61665343894907, "count": 232061, "self": 142.14311326194849, "children": { "RLTrainer._checkpoint": { "total": 0.4735401770005865, "count": 4, "self": 0.4735401770005865 } } }, "_update_policy": { "total": 312.97163801999966, "count": 97, "self": 259.1188763809937, "children": { "TorchPPOOptimizer.update": { "total": 53.85276163900596, "count": 2910, "self": 53.85276163900596 } } } } } } }, "trainer_threads": { "total": 9.72999714576872e-07, "count": 1, "self": 9.72999714576872e-07 }, "TrainerController._save_models": { "total": 0.111687818000064, "count": 1, "self": 0.0019724620001397852, "children": { "RLTrainer._checkpoint": { "total": 0.10971535599992421, "count": 1, "self": 0.10971535599992421 } } } } } } }