{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4079982042312622, "min": 1.4079982042312622, "max": 1.430060625076294, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69111.59375, "min": 67982.0625, "max": 77642.359375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 127.13076923076923, "min": 104.5126582278481, "max": 394.2992125984252, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49581.0, "min": 48823.0, "max": 50276.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999271.0, "min": 49833.0, "max": 1999271.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999271.0, "min": 49833.0, "max": 1999271.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.239614963531494, "min": 0.12229996919631958, "max": 2.3335297107696533, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 873.4498291015625, "min": 15.654396057128906, "max": 1101.83056640625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.3267115658674484, "min": 1.82798195281066, "max": 3.8103689542523136, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1297.417510688305, "min": 233.98168995976448, "max": 1733.7639011740685, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.3267115658674484, "min": 1.82798195281066, "max": 3.8103689542523136, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1297.417510688305, "min": 233.98168995976448, "max": 1733.7639011740685, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.0181610560316282, "min": 0.01374271792289316, "max": 0.019941217913583387, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0544831680948846, "min": 0.02748543584578632, "max": 0.05944081839619457, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04461875299198761, "min": 0.019623157723496355, "max": 0.05843788702040911, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.13385625897596282, "min": 0.03924631544699271, "max": 0.16589974525074164, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.339948886716666e-06, "min": 3.339948886716666e-06, "max": 0.00029531737656087495, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0019846660149999e-05, "min": 1.0019846660149999e-05, "max": 0.0008439646686784498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10111328333333335, "min": 0.10111328333333335, "max": 0.19843912500000005, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30333985, "min": 0.2073701, "max": 0.5813215500000003, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.555283833333333e-05, "min": 6.555283833333333e-05, "max": 0.004922112337500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.000196658515, "min": 0.000196658515, "max": 0.014067945345, "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": "1679494033", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1679496327" }, "total": 2294.0607697369996, "count": 1, "self": 0.38851176099979057, "children": { "run_training.setup": { "total": 0.10385786099993766, "count": 1, "self": 0.10385786099993766 }, "TrainerController.start_learning": { "total": 2293.568400115, "count": 1, "self": 4.157648828946094, "children": { "TrainerController._reset_env": { "total": 9.40167170799998, "count": 1, "self": 9.40167170799998 }, "TrainerController.advance": { "total": 2279.8898681660535, "count": 230795, "self": 4.550865952867753, "children": { "env_step": { "total": 1784.0181929770988, "count": 230795, "self": 1501.2411198970167, "children": { "SubprocessEnvManager._take_step": { "total": 280.05010400705055, "count": 230795, "self": 16.727880701086292, "children": { "TorchPolicy.evaluate": { "total": 263.32222330596426, "count": 223004, "self": 263.32222330596426 } } }, "workers": { "total": 2.7269690730316825, "count": 230795, "self": 0.0, "children": { "worker_root": { "total": 2285.9125111610415, "count": 230795, "is_parallel": true, "self": 1063.3022828330827, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009216780000542713, "count": 1, "is_parallel": true, "self": 0.000245884000037222, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006757940000170493, "count": 2, "is_parallel": true, "self": 0.0006757940000170493 } } }, "UnityEnvironment.step": { "total": 0.028423812000028192, "count": 1, "is_parallel": true, "self": 0.0003070459999889863, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019812099992577714, "count": 1, "is_parallel": true, "self": 0.00019812099992577714 }, "communicator.exchange": { "total": 0.027241888000048675, "count": 1, "is_parallel": true, "self": 0.027241888000048675 }, "steps_from_proto": { "total": 0.0006767570000647538, "count": 1, "is_parallel": true, "self": 0.00019561800002065866, "children": { "_process_rank_one_or_two_observation": { "total": 0.00048113900004409516, "count": 2, "is_parallel": true, "self": 0.00048113900004409516 } } } } } } }, "UnityEnvironment.step": { "total": 1222.6102283279588, "count": 230794, "is_parallel": true, "self": 37.23429625091421, "children": { "UnityEnvironment._generate_step_input": { "total": 75.96251914304605, "count": 230794, "is_parallel": true, "self": 75.96251914304605 }, "communicator.exchange": { "total": 1022.3762059579976, "count": 230794, "is_parallel": true, "self": 1022.3762059579976 }, "steps_from_proto": { "total": 87.0372069760009, "count": 230794, "is_parallel": true, "self": 32.66117222001367, "children": { "_process_rank_one_or_two_observation": { "total": 54.376034755987234, "count": 461588, "is_parallel": true, "self": 54.376034755987234 } } } } } } } } } } }, "trainer_advance": { "total": 491.3208092360868, "count": 230795, "self": 6.2989551130276595, "children": { "process_trajectory": { "total": 134.50847889106092, "count": 230795, "self": 133.22746693506042, "children": { "RLTrainer._checkpoint": { "total": 1.2810119560004978, "count": 10, "self": 1.2810119560004978 } } }, "_update_policy": { "total": 350.5133752319982, "count": 97, "self": 292.7103768630043, "children": { "TorchPPOOptimizer.update": { "total": 57.80299836899394, "count": 2910, "self": 57.80299836899394 } } } } } } }, "trainer_threads": { "total": 9.43000031838892e-07, "count": 1, "self": 9.43000031838892e-07 }, "TrainerController._save_models": { "total": 0.11921046900033616, "count": 1, "self": 0.0022256280003603024, "children": { "RLTrainer._checkpoint": { "total": 0.11698484099997586, "count": 1, "self": 0.11698484099997586 } } } } } } }