{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4031606912612915, "min": 1.4031606912612915, "max": 1.4305899143218994, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68318.4921875, "min": 68318.4921875, "max": 77286.5078125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 97.47637795275591, "min": 91.48613678373383, "max": 427.12820512820514, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49518.0, "min": 49269.0, "max": 49996.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999957.0, "min": 49535.0, "max": 1999957.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999957.0, "min": 49535.0, "max": 1999957.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.401588201522827, "min": 0.11879417300224304, "max": 2.4537761211395264, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1220.0068359375, "min": 13.780123710632324, "max": 1292.2996826171875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.691757331917605, "min": 1.8268774023986067, "max": 3.8728205352339127, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1875.4127246141434, "min": 211.9177786782384, "max": 2038.2946839928627, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.691757331917605, "min": 1.8268774023986067, "max": 3.8728205352339127, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1875.4127246141434, "min": 211.9177786782384, "max": 2038.2946839928627, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01594847146285853, "min": 0.013837479357607662, "max": 0.0208747938197727, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04784541438857559, "min": 0.027674958715215324, "max": 0.06209199309135632, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.052815063380532795, "min": 0.02121256149063508, "max": 0.06497909718503556, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15844519014159839, "min": 0.04242512298127016, "max": 0.1938975614806016, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.500998833033328e-06, "min": 3.500998833033328e-06, "max": 0.00029535030154989996, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0502996499099985e-05, "min": 1.0502996499099985e-05, "max": 0.00084415186861605, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10116696666666668, "min": 0.10116696666666668, "max": 0.19845010000000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3035009, "min": 0.20746819999999994, "max": 0.58138395, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.823163666666659e-05, "min": 6.823163666666659e-05, "max": 0.0049226599900000015, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020469490999999978, "min": 0.00020469490999999978, "max": 0.014071059105, "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": "1718163120", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1718165515" }, "total": 2395.0833436000003, "count": 1, "self": 0.44002277700019476, "children": { "run_training.setup": { "total": 0.05489981599998828, "count": 1, "self": 0.05489981599998828 }, "TrainerController.start_learning": { "total": 2394.588421007, "count": 1, "self": 4.25351641411271, "children": { "TrainerController._reset_env": { "total": 3.121530925000002, "count": 1, "self": 3.121530925000002 }, "TrainerController.advance": { "total": 2387.1053030258868, "count": 231426, "self": 4.558667795752626, "children": { "env_step": { "total": 1896.2277404350405, "count": 231426, "self": 1566.740089340123, "children": { "SubprocessEnvManager._take_step": { "total": 326.5798464928713, "count": 231426, "self": 16.13639955981955, "children": { "TorchPolicy.evaluate": { "total": 310.44344693305175, "count": 222908, "self": 310.44344693305175 } } }, "workers": { "total": 2.9078046020462125, "count": 231426, "self": 0.0, "children": { "worker_root": { "total": 2387.475919477059, "count": 231426, "is_parallel": true, "self": 1125.1988674410397, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008477149999635003, "count": 1, "is_parallel": true, "self": 0.00023199199995360686, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006157230000098934, "count": 2, "is_parallel": true, "self": 0.0006157230000098934 } } }, "UnityEnvironment.step": { "total": 0.030232795000074475, "count": 1, "is_parallel": true, "self": 0.0004254710001987405, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020912799993766384, "count": 1, "is_parallel": true, "self": 0.00020912799993766384 }, "communicator.exchange": { "total": 0.028828643999986525, "count": 1, "is_parallel": true, "self": 0.028828643999986525 }, "steps_from_proto": { "total": 0.0007695519999515454, "count": 1, "is_parallel": true, "self": 0.0002154179998115069, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005541340001400386, "count": 2, "is_parallel": true, "self": 0.0005541340001400386 } } } } } } }, "UnityEnvironment.step": { "total": 1262.2770520360193, "count": 231425, "is_parallel": true, "self": 39.23908130518089, "children": { "UnityEnvironment._generate_step_input": { "total": 79.93965012191495, "count": 231425, "is_parallel": true, "self": 79.93965012191495 }, "communicator.exchange": { "total": 1054.2429853749636, "count": 231425, "is_parallel": true, "self": 1054.2429853749636 }, "steps_from_proto": { "total": 88.85533523395998, "count": 231425, "is_parallel": true, "self": 31.250304089127553, "children": { "_process_rank_one_or_two_observation": { "total": 57.605031144832424, "count": 462850, "is_parallel": true, "self": 57.605031144832424 } } } } } } } } } } }, "trainer_advance": { "total": 486.3188947950937, "count": 231426, "self": 6.402561366133796, "children": { "process_trajectory": { "total": 149.29045756096127, "count": 231426, "self": 147.7652426649612, "children": { "RLTrainer._checkpoint": { "total": 1.5252148960000795, "count": 10, "self": 1.5252148960000795 } } }, "_update_policy": { "total": 330.6258758679986, "count": 97, "self": 266.92791378900347, "children": { "TorchPPOOptimizer.update": { "total": 63.69796207899515, "count": 2910, "self": 63.69796207899515 } } } } } } }, "trainer_threads": { "total": 7.520002327510156e-07, "count": 1, "self": 7.520002327510156e-07 }, "TrainerController._save_models": { "total": 0.10806989000002432, "count": 1, "self": 0.0018455219997122185, "children": { "RLTrainer._checkpoint": { "total": 0.1062243680003121, "count": 1, "self": 0.1062243680003121 } } } } } } }