{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4069163799285889, "min": 1.4069163799285889, "max": 1.4281541109085083, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68415.53125, "min": 68397.375, "max": 77389.390625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 109.69911504424779, "min": 86.86643233743409, "max": 377.81954887218046, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49584.0, "min": 48857.0, "max": 50250.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999997.0, "min": 49827.0, "max": 1999997.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999997.0, "min": 49827.0, "max": 1999997.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.2900469303131104, "min": 0.11471264064311981, "max": 2.4330332279205322, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1035.1011962890625, "min": 15.142068862915039, "max": 1365.7037353515625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.4521645360288367, "min": 1.7969717611417626, "max": 4.029047752119774, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1560.3783702850342, "min": 237.20027247071266, "max": 2208.778769135475, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.4521645360288367, "min": 1.7969717611417626, "max": 4.029047752119774, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1560.3783702850342, "min": 237.20027247071266, "max": 2208.778769135475, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016267674929258645, "min": 0.012782194501111614, "max": 0.018992772999141986, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03253534985851729, "min": 0.02556438900222323, "max": 0.05537922002962053, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04480398589124282, "min": 0.021703821855286756, "max": 0.0663084766931004, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.08960797178248564, "min": 0.04340764371057351, "max": 0.1989254300793012, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.3366735544749906e-06, "min": 4.3366735544749906e-06, "max": 0.00029530852656382497, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.673347108949981e-06, "min": 8.673347108949981e-06, "max": 0.0008440054686648499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10144552499999998, "min": 0.10144552499999998, "max": 0.198436175, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20289104999999996, "min": 0.20289104999999996, "max": 0.58133515, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.213169749999987e-05, "min": 8.213169749999987e-05, "max": 0.004921965132500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00016426339499999975, "min": 0.00016426339499999975, "max": 0.014068623984999999, "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": "1673888314", "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": "1673890483" }, "total": 2169.096703059, "count": 1, "self": 0.3822705049997239, "children": { "run_training.setup": { "total": 0.10899761099994976, "count": 1, "self": 0.10899761099994976 }, "TrainerController.start_learning": { "total": 2168.605434943, "count": 1, "self": 3.5596683979715635, "children": { "TrainerController._reset_env": { "total": 11.17840778599998, "count": 1, "self": 11.17840778599998 }, "TrainerController.advance": { "total": 2153.7494518510284, "count": 231734, "self": 3.7657392178584814, "children": { "env_step": { "total": 1695.9576125730841, "count": 231734, "self": 1423.1001615731982, "children": { "SubprocessEnvManager._take_step": { "total": 270.3736486118855, "count": 231734, "self": 14.09824973990112, "children": { "TorchPolicy.evaluate": { "total": 256.2753988719844, "count": 222963, "self": 64.83668972103237, "children": { "TorchPolicy.sample_actions": { "total": 191.43870915095204, "count": 222963, "self": 191.43870915095204 } } } } }, "workers": { "total": 2.483802388000413, "count": 231734, "self": 0.0, "children": { "worker_root": { "total": 2160.994592873941, "count": 231734, "is_parallel": true, "self": 989.0844839879726, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002388611000014862, "count": 1, "is_parallel": true, "self": 0.0003069370000048366, "children": { "_process_rank_one_or_two_observation": { "total": 0.0020816740000100253, "count": 2, "is_parallel": true, "self": 0.0020816740000100253 } } }, "UnityEnvironment.step": { "total": 0.027915673000052266, "count": 1, "is_parallel": true, "self": 0.00027574800014917855, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022606700008509506, "count": 1, "is_parallel": true, "self": 0.00022606700008509506 }, "communicator.exchange": { "total": 0.026500053999825468, "count": 1, "is_parallel": true, "self": 0.026500053999825468 }, "steps_from_proto": { "total": 0.000913803999992524, "count": 1, "is_parallel": true, "self": 0.0002553699998770753, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006584340001154487, "count": 2, "is_parallel": true, "self": 0.0006584340001154487 } } } } } } }, "UnityEnvironment.step": { "total": 1171.9101088859686, "count": 231733, "is_parallel": true, "self": 34.24812822796707, "children": { "UnityEnvironment._generate_step_input": { "total": 76.25468262002755, "count": 231733, "is_parallel": true, "self": 76.25468262002755 }, "communicator.exchange": { "total": 969.5842866000066, "count": 231733, "is_parallel": true, "self": 969.5842866000066 }, "steps_from_proto": { "total": 91.82301143796735, "count": 231733, "is_parallel": true, "self": 37.629003750822676, "children": { "_process_rank_one_or_two_observation": { "total": 54.194007687144676, "count": 463466, "is_parallel": true, "self": 54.194007687144676 } } } } } } } } } } }, "trainer_advance": { "total": 454.0261000600858, "count": 231734, "self": 5.732851683095305, "children": { "process_trajectory": { "total": 141.57075838499009, "count": 231734, "self": 140.37955435698996, "children": { "RLTrainer._checkpoint": { "total": 1.1912040280001293, "count": 10, "self": 1.1912040280001293 } } }, "_update_policy": { "total": 306.7224899920004, "count": 96, "self": 253.90944237000508, "children": { "TorchPPOOptimizer.update": { "total": 52.81304762199534, "count": 2880, "self": 52.81304762199534 } } } } } } }, "trainer_threads": { "total": 7.31999989511678e-07, "count": 1, "self": 7.31999989511678e-07 }, "TrainerController._save_models": { "total": 0.11790617599990583, "count": 1, "self": 0.002087835999645904, "children": { "RLTrainer._checkpoint": { "total": 0.11581834000025992, "count": 1, "self": 0.11581834000025992 } } } } } } }