{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4031422138214111, "min": 1.4031422138214111, "max": 1.4265025854110718, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69842.8046875, "min": 69243.140625, "max": 77353.3125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 71.53846153846153, "min": 68.59666203059805, "max": 396.73015873015873, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49290.0, "min": 49141.0, "max": 49988.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999972.0, "min": 49607.0, "max": 1999972.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999972.0, "min": 49607.0, "max": 1999972.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.5071768760681152, "min": 0.054324954748153687, "max": 2.6004130840301514, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1727.44482421875, "min": 6.790619373321533, "max": 1786.722900390625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.957180421134384, "min": 1.864990885257721, "max": 4.072501356278674, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2726.4973101615906, "min": 233.12386065721512, "max": 2820.650517106056, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.957180421134384, "min": 1.864990885257721, "max": 4.072501356278674, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2726.4973101615906, "min": 233.12386065721512, "max": 2820.650517106056, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.014632494502196398, "min": 0.013420333070340955, "max": 0.020311314635910092, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.043897483506589195, "min": 0.02684066614068191, "max": 0.053278862696606664, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06285831154220634, "min": 0.022217703672746815, "max": 0.06584098976519372, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.188574934626619, "min": 0.04443540734549363, "max": 0.19752296929558116, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.797548734183325e-06, "min": 3.797548734183325e-06, "max": 0.000295287076570975, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1392646202549975e-05, "min": 1.1392646202549975e-05, "max": 0.0008437626187457999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10126581666666667, "min": 0.10126581666666667, "max": 0.19842902499999998, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30379745, "min": 0.2076658, "max": 0.5812542, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.316425166666652e-05, "min": 7.316425166666652e-05, "max": 0.004921608347500002, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021949275499999956, "min": 0.00021949275499999956, "max": 0.014064584580000001, "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": "1696504600", "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": "1696507218" }, "total": 2617.497871965, "count": 1, "self": 0.43220886299968697, "children": { "run_training.setup": { "total": 0.04365879500005576, "count": 1, "self": 0.04365879500005576 }, "TrainerController.start_learning": { "total": 2617.022004307, "count": 1, "self": 4.924700287063388, "children": { "TrainerController._reset_env": { "total": 4.121726712000054, "count": 1, "self": 4.121726712000054 }, "TrainerController.advance": { "total": 2607.844808241937, "count": 233481, "self": 4.976932092059997, "children": { "env_step": { "total": 2027.2449180879903, "count": 233481, "self": 1710.680709765963, "children": { "SubprocessEnvManager._take_step": { "total": 313.3421407388546, "count": 233481, "self": 17.811487623938092, "children": { "TorchPolicy.evaluate": { "total": 295.5306531149165, "count": 222916, "self": 295.5306531149165 } } }, "workers": { "total": 3.2220675831725885, "count": 233481, "self": 0.0, "children": { "worker_root": { "total": 2608.799341807931, "count": 233481, "is_parallel": true, "self": 1214.9109889368797, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010957599999983358, "count": 1, "is_parallel": true, "self": 0.0003392999999505264, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007564600000478094, "count": 2, "is_parallel": true, "self": 0.0007564600000478094 } } }, "UnityEnvironment.step": { "total": 0.031361062999962996, "count": 1, "is_parallel": true, "self": 0.00034641299998838804, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00026658100000531704, "count": 1, "is_parallel": true, "self": 0.00026658100000531704 }, "communicator.exchange": { "total": 0.029963377000058244, "count": 1, "is_parallel": true, "self": 0.029963377000058244 }, "steps_from_proto": { "total": 0.0007846919999110469, "count": 1, "is_parallel": true, "self": 0.0002345429999195403, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005501489999915066, "count": 2, "is_parallel": true, "self": 0.0005501489999915066 } } } } } } }, "UnityEnvironment.step": { "total": 1393.8883528710512, "count": 233480, "is_parallel": true, "self": 41.81509814800438, "children": { "UnityEnvironment._generate_step_input": { "total": 88.11589912696297, "count": 233480, "is_parallel": true, "self": 88.11589912696297 }, "communicator.exchange": { "total": 1158.1010508209815, "count": 233480, "is_parallel": true, "self": 1158.1010508209815 }, "steps_from_proto": { "total": 105.8563047751021, "count": 233480, "is_parallel": true, "self": 39.75852158304883, "children": { "_process_rank_one_or_two_observation": { "total": 66.09778319205327, "count": 466960, "is_parallel": true, "self": 66.09778319205327 } } } } } } } } } } }, "trainer_advance": { "total": 575.6229580618865, "count": 233481, "self": 7.255331477949312, "children": { "process_trajectory": { "total": 157.63371978993666, "count": 233481, "self": 156.18314430293674, "children": { "RLTrainer._checkpoint": { "total": 1.4505754869999237, "count": 10, "self": 1.4505754869999237 } } }, "_update_policy": { "total": 410.7339067940005, "count": 97, "self": 349.6499598000046, "children": { "TorchPPOOptimizer.update": { "total": 61.08394699399594, "count": 2910, "self": 61.08394699399594 } } } } } } }, "trainer_threads": { "total": 1.0709995876823086e-06, "count": 1, "self": 1.0709995876823086e-06 }, "TrainerController._save_models": { "total": 0.130767995000042, "count": 1, "self": 0.0022886970000399742, "children": { "RLTrainer._checkpoint": { "total": 0.12847929800000202, "count": 1, "self": 0.12847929800000202 } } } } } } }