{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4021565914154053, "min": 1.4021565914154053, "max": 1.4240217208862305, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69144.546875, "min": 69144.546875, "max": 76093.34375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 79.5562805872757, "min": 74.28614457831326, "max": 355.93617021276594, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48768.0, "min": 48768.0, "max": 50187.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999945.0, "min": 49981.0, "max": 1999945.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999945.0, "min": 49981.0, "max": 1999945.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.443033456802368, "min": 0.08339297026395798, "max": 2.5030975341796875, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1497.5794677734375, "min": 11.675015449523926, "max": 1640.6251220703125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.773921971997857, "min": 1.8578072349940027, "max": 4.025800640623825, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2313.4141688346863, "min": 260.0930128991604, "max": 2596.825870335102, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.773921971997857, "min": 1.8578072349940027, "max": 4.025800640623825, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2313.4141688346863, "min": 260.0930128991604, "max": 2596.825870335102, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01923707592941355, "min": 0.014401750129278905, "max": 0.019733475679014293, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05771122778824065, "min": 0.02880350025855781, "max": 0.059200427037042876, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05548375012973945, "min": 0.02190955678621928, "max": 0.06397183127701284, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16645125038921835, "min": 0.04381911357243856, "max": 0.18550109453499317, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.9511986829666624e-06, "min": 3.9511986829666624e-06, "max": 0.00029527822657392504, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1853596048899988e-05, "min": 1.1853596048899988e-05, "max": 0.00084402736865755, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10131703333333336, "min": 0.10131703333333336, "max": 0.198426075, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3039511000000001, "min": 0.20776685000000003, "max": 0.58134245, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.571996333333328e-05, "min": 7.571996333333328e-05, "max": 0.0049214611425, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022715988999999986, "min": 0.00022715988999999986, "max": 0.014068988255, "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": "1691186414", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1691188499" }, "total": 2085.831384167, "count": 1, "self": 0.37616893000040363, "children": { "run_training.setup": { "total": 0.04184466700007761, "count": 1, "self": 0.04184466700007761 }, "TrainerController.start_learning": { "total": 2085.4133705699996, "count": 1, "self": 4.2799399339291995, "children": { "TrainerController._reset_env": { "total": 3.9575025760000244, "count": 1, "self": 3.9575025760000244 }, "TrainerController.advance": { "total": 2077.0383485170705, "count": 233196, "self": 4.26955251709478, "children": { "env_step": { "total": 1603.1945979949744, "count": 233196, "self": 1325.545094936043, "children": { "SubprocessEnvManager._take_step": { "total": 274.87312780789716, "count": 233196, "self": 15.289915307888577, "children": { "TorchPolicy.evaluate": { "total": 259.5832125000086, "count": 222957, "self": 259.5832125000086 } } }, "workers": { "total": 2.776375251034324, "count": 233196, "self": 0.0, "children": { "worker_root": { "total": 2077.645741425985, "count": 233196, "is_parallel": true, "self": 1006.5291888759039, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008297960000618332, "count": 1, "is_parallel": true, "self": 0.00020445499990273674, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006253410001590964, "count": 2, "is_parallel": true, "self": 0.0006253410001590964 } } }, "UnityEnvironment.step": { "total": 0.020012966999956916, "count": 1, "is_parallel": true, "self": 0.00019256099994890974, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018994800007021695, "count": 1, "is_parallel": true, "self": 0.00018994800007021695 }, "communicator.exchange": { "total": 0.019190956999864284, "count": 1, "is_parallel": true, "self": 0.019190956999864284 }, "steps_from_proto": { "total": 0.00043950100007350557, "count": 1, "is_parallel": true, "self": 0.0001399679999849468, "children": { "_process_rank_one_or_two_observation": { "total": 0.00029953300008855877, "count": 2, "is_parallel": true, "self": 0.00029953300008855877 } } } } } } }, "UnityEnvironment.step": { "total": 1071.116552550081, "count": 233195, "is_parallel": true, "self": 32.41846026424287, "children": { "UnityEnvironment._generate_step_input": { "total": 64.65728868091105, "count": 233195, "is_parallel": true, "self": 64.65728868091105 }, "communicator.exchange": { "total": 893.9506182780087, "count": 233195, "is_parallel": true, "self": 893.9506182780087 }, "steps_from_proto": { "total": 80.09018532691834, "count": 233195, "is_parallel": true, "self": 30.32104824788894, "children": { "_process_rank_one_or_two_observation": { "total": 49.769137079029406, "count": 466390, "is_parallel": true, "self": 49.769137079029406 } } } } } } } } } } }, "trainer_advance": { "total": 469.57419800500134, "count": 233196, "self": 6.0573780169254405, "children": { "process_trajectory": { "total": 129.91762671007814, "count": 233196, "self": 128.70855760507789, "children": { "RLTrainer._checkpoint": { "total": 1.2090691050002533, "count": 10, "self": 1.2090691050002533 } } }, "_update_policy": { "total": 333.59919327799776, "count": 97, "self": 289.6085598280047, "children": { "TorchPPOOptimizer.update": { "total": 43.990633449993084, "count": 2910, "self": 43.990633449993084 } } } } } } }, "trainer_threads": { "total": 1.011999756883597e-06, "count": 1, "self": 1.011999756883597e-06 }, "TrainerController._save_models": { "total": 0.13757853100014472, "count": 1, "self": 0.0020795870004803874, "children": { "RLTrainer._checkpoint": { "total": 0.13549894399966433, "count": 1, "self": 0.13549894399966433 } } } } } } }