{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4050071239471436, "min": 1.4050071239471436, "max": 1.426387906074524, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70718.2265625, "min": 68825.2734375, "max": 76291.8515625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 96.89126213592233, "min": 81.88538205980066, "max": 401.608, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49899.0, "min": 48952.0, "max": 50201.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999701.0, "min": 49796.0, "max": 1999701.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999701.0, "min": 49796.0, "max": 1999701.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.453686237335205, "min": 0.1696585714817047, "max": 2.453686237335205, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1263.6484375, "min": 21.037662506103516, "max": 1432.41064453125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.795067819808293, "min": 1.7044149959279644, "max": 3.9170844981187507, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1954.459927201271, "min": 211.3474594950676, "max": 2254.5267612934113, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.795067819808293, "min": 1.7044149959279644, "max": 3.9170844981187507, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1954.459927201271, "min": 211.3474594950676, "max": 2254.5267612934113, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01696865379085971, "min": 0.013465692579241781, "max": 0.019167682963598054, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.050905961372579134, "min": 0.029024775302483857, "max": 0.056315791975551595, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04948229644861487, "min": 0.02170841939126452, "max": 0.06007846500724554, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1484468893458446, "min": 0.04341683878252904, "max": 0.17751614153385162, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.485648838150005e-06, "min": 3.485648838150005e-06, "max": 0.00029532892655702493, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0456946514450015e-05, "min": 1.0456946514450015e-05, "max": 0.0008439271686909498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10116185000000001, "min": 0.10116185000000001, "max": 0.198442975, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30348555000000005, "min": 0.20745725000000004, "max": 0.58130905, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.797631500000006e-05, "min": 6.797631500000006e-05, "max": 0.004922304452500002, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020392894500000018, "min": 0.00020392894500000018, "max": 0.014067321594999998, "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": "1704202666", "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=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1704205326" }, "total": 2660.0374785860004, "count": 1, "self": 0.4436828240000068, "children": { "run_training.setup": { "total": 0.0530582860000095, "count": 1, "self": 0.0530582860000095 }, "TrainerController.start_learning": { "total": 2659.5407374760002, "count": 1, "self": 4.940123021919135, "children": { "TrainerController._reset_env": { "total": 3.533514467000032, "count": 1, "self": 3.533514467000032 }, "TrainerController.advance": { "total": 2650.949771638081, "count": 232201, "self": 5.321337281051001, "children": { "env_step": { "total": 2120.405749167987, "count": 232201, "self": 1759.805223766867, "children": { "SubprocessEnvManager._take_step": { "total": 357.33101110605253, "count": 232201, "self": 18.474365114999046, "children": { "TorchPolicy.evaluate": { "total": 338.8566459910535, "count": 223057, "self": 338.8566459910535 } } }, "workers": { "total": 3.269514295067438, "count": 232201, "self": 0.0, "children": { "worker_root": { "total": 2651.5107919040447, "count": 232201, "is_parallel": true, "self": 1225.6653114250807, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0007583249999925101, "count": 1, "is_parallel": true, "self": 0.00022772100010115537, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005306039998913548, "count": 2, "is_parallel": true, "self": 0.0005306039998913548 } } }, "UnityEnvironment.step": { "total": 0.056720140000038555, "count": 1, "is_parallel": true, "self": 0.00035309800000504765, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002360350000571998, "count": 1, "is_parallel": true, "self": 0.0002360350000571998 }, "communicator.exchange": { "total": 0.055432107999990876, "count": 1, "is_parallel": true, "self": 0.055432107999990876 }, "steps_from_proto": { "total": 0.0006988989999854311, "count": 1, "is_parallel": true, "self": 0.00020040399999743386, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004984949999879973, "count": 2, "is_parallel": true, "self": 0.0004984949999879973 } } } } } } }, "UnityEnvironment.step": { "total": 1425.845480478964, "count": 232200, "is_parallel": true, "self": 43.85953751792431, "children": { "UnityEnvironment._generate_step_input": { "total": 91.46350131708698, "count": 232200, "is_parallel": true, "self": 91.46350131708698 }, "communicator.exchange": { "total": 1191.497763845981, "count": 232200, "is_parallel": true, "self": 1191.497763845981 }, "steps_from_proto": { "total": 99.02467779797178, "count": 232200, "is_parallel": true, "self": 36.77203550998513, "children": { "_process_rank_one_or_two_observation": { "total": 62.252642287986646, "count": 464400, "is_parallel": true, "self": 62.252642287986646 } } } } } } } } } } }, "trainer_advance": { "total": 525.2226851890431, "count": 232201, "self": 7.691728144075455, "children": { "process_trajectory": { "total": 171.7003202749671, "count": 232201, "self": 170.34449415996698, "children": { "RLTrainer._checkpoint": { "total": 1.3558261150001272, "count": 10, "self": 1.3558261150001272 } } }, "_update_policy": { "total": 345.8306367700005, "count": 97, "self": 280.427845747997, "children": { "TorchPPOOptimizer.update": { "total": 65.4027910220035, "count": 2910, "self": 65.4027910220035 } } } } } } }, "trainer_threads": { "total": 8.400002116104588e-07, "count": 1, "self": 8.400002116104588e-07 }, "TrainerController._save_models": { "total": 0.1173275090000061, "count": 1, "self": 0.0021309479998308234, "children": { "RLTrainer._checkpoint": { "total": 0.11519656100017528, "count": 1, "self": 0.11519656100017528 } } } } } } }