{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4038997888565063, "min": 1.4038997888565063, "max": 1.424918293952942, "count": 26 }, "Huggy.Policy.Entropy.sum": { "value": 69838.3984375, "min": 69433.0859375, "max": 76239.21875, "count": 26 }, "Huggy.Environment.EpisodeLength.mean": { "value": 71.21820809248555, "min": 68.0621546961326, "max": 420.45, "count": 26 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49283.0, "min": 49227.0, "max": 50454.0, "count": 26 }, "Huggy.Step.mean": { "value": 1299950.0, "min": 49902.0, "max": 1299950.0, "count": 26 }, "Huggy.Step.sum": { "value": 1299950.0, "min": 49902.0, "max": 1299950.0, "count": 26 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.2132790088653564, "min": -0.0050509232096374035, "max": 2.2245519161224365, "count": 26 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1531.589111328125, "min": -0.6010598540306091, "max": 1581.6563720703125, "count": 26 }, "Huggy.Environment.CumulativeReward.mean": { "value": 4.016878309019039, "min": 1.7115899226745637, "max": 4.0645961599804785, "count": 26 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2779.679789841175, "min": 203.6792007982731, "max": 2858.101459980011, "count": 26 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 4.016878309019039, "min": 1.7115899226745637, "max": 4.0645961599804785, "count": 26 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2779.679789841175, "min": 203.6792007982731, "max": 2858.101459980011, "count": 26 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01818725565309352, "min": 0.013398074267994768, "max": 0.021402372522546405, "count": 26 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.054561766959280555, "min": 0.026796148535989536, "max": 0.05517984676674435, "count": 26 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.046650495049026276, "min": 0.021238714829087256, "max": 0.04905991993016667, "count": 26 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.13995148514707884, "min": 0.04247742965817451, "max": 0.14717975979050002, "count": 26 }, "Huggy.Policy.LearningRate.mean": { "value": 0.00010884136371956666, "min": 0.00010884136371956666, "max": 0.00029536155154614996, "count": 26 }, "Huggy.Policy.LearningRate.sum": { "value": 0.00032652409115869997, "min": 0.00023306652231119991, "max": 0.0008444352185215998, "count": 26 }, "Huggy.Policy.Epsilon.mean": { "value": 0.13628043333333334, "min": 0.13628043333333334, "max": 0.19845385000000001, "count": 26 }, "Huggy.Policy.Epsilon.sum": { "value": 0.4088413, "min": 0.27768880000000007, "max": 0.5814784, "count": 26 }, "Huggy.Policy.Beta.mean": { "value": 0.0018203936233333335, "min": 0.0018203936233333335, "max": 0.004922847115, "count": 26 }, "Huggy.Policy.Beta.sum": { "value": 0.00546118087, "min": 0.0038966711200000004, "max": 0.014075772160000001, "count": 26 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 26 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 26 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1670528658", "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": "1670530796" }, "total": 2138.3108221720004, "count": 1, "self": 0.26674200700017536, "children": { "run_training.setup": { "total": 0.12684074300000248, "count": 1, "self": 0.12684074300000248 }, "TrainerController.start_learning": { "total": 2137.917239422, "count": 1, "self": 4.547979873061649, "children": { "TrainerController._reset_env": { "total": 11.157103425000003, "count": 1, "self": 11.157103425000003 }, "TrainerController.advance": { "total": 2121.993839581938, "count": 154886, "self": 4.616334345897485, "children": { "env_step": { "total": 1730.2653651370408, "count": 154886, "self": 1441.292321369046, "children": { "SubprocessEnvManager._take_step": { "total": 285.74260372599457, "count": 154886, "self": 15.789832451023528, "children": { "TorchPolicy.evaluate": { "total": 269.95277127497104, "count": 148153, "self": 70.06429841796637, "children": { "TorchPolicy.sample_actions": { "total": 199.88847285700467, "count": 148153, "self": 199.88847285700467 } } } } }, "workers": { "total": 3.230440042000282, "count": 154885, "self": 0.0, "children": { "worker_root": { "total": 2129.5005112859862, "count": 154885, "is_parallel": true, "self": 963.8439002089617, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0018342470000334288, "count": 1, "is_parallel": true, "self": 0.0003768180000633947, "children": { "_process_rank_one_or_two_observation": { "total": 0.001457428999970034, "count": 2, "is_parallel": true, "self": 0.001457428999970034 } } }, "UnityEnvironment.step": { "total": 0.03187894400002733, "count": 1, "is_parallel": true, "self": 0.00030034900004238807, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020491199995831266, "count": 1, "is_parallel": true, "self": 0.00020491199995831266 }, "communicator.exchange": { "total": 0.030557170999998107, "count": 1, "is_parallel": true, "self": 0.030557170999998107 }, "steps_from_proto": { "total": 0.0008165120000285242, "count": 1, "is_parallel": true, "self": 0.0002890360000264991, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005274760000020251, "count": 2, "is_parallel": true, "self": 0.0005274760000020251 } } } } } } }, "UnityEnvironment.step": { "total": 1165.6566110770245, "count": 154884, "is_parallel": true, "self": 32.519965384932675, "children": { "UnityEnvironment._generate_step_input": { "total": 68.38158529300762, "count": 154884, "is_parallel": true, "self": 68.38158529300762 }, "communicator.exchange": { "total": 977.8697659180075, "count": 154884, "is_parallel": true, "self": 977.8697659180075 }, "steps_from_proto": { "total": 86.88529448107664, "count": 154884, "is_parallel": true, "self": 35.84984210203618, "children": { "_process_rank_one_or_two_observation": { "total": 51.035452379040464, "count": 309768, "is_parallel": true, "self": 51.035452379040464 } } } } } } } } } } }, "trainer_advance": { "total": 387.11214009900004, "count": 154885, "self": 7.397319591023802, "children": { "process_trajectory": { "total": 137.52867146497624, "count": 154885, "self": 137.2365648679763, "children": { "RLTrainer._checkpoint": { "total": 0.292106596999929, "count": 2, "self": 0.292106596999929 } } }, "_update_policy": { "total": 242.186149043, "count": 64, "self": 201.8716260270042, "children": { "TorchPPOOptimizer.update": { "total": 40.3145230159958, "count": 1920, "self": 40.3145230159958 } } } } } } }, "trainer_threads": { "total": 1.8020000425167382e-06, "count": 1, "self": 1.8020000425167382e-06 }, "TrainerController._save_models": { "total": 0.2183147400000962, "count": 1, "self": 0.0031105380003282335, "children": { "RLTrainer._checkpoint": { "total": 0.21520420199976797, "count": 1, "self": 0.21520420199976797 } } } } } } }