{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.404952883720398, "min": 1.404952883720398, "max": 1.4259700775146484, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70513.1796875, "min": 69102.6015625, "max": 76256.5, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 83.0954003407155, "min": 79.79806138933765, "max": 398.14285714285717, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48777.0, "min": 48653.0, "max": 50166.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999975.0, "min": 49796.0, "max": 1999975.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999975.0, "min": 49796.0, "max": 1999975.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.497999429702759, "min": 0.12087757885456085, "max": 2.497999429702759, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1466.32568359375, "min": 15.109697341918945, "max": 1511.77734375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.907958653249367, "min": 1.9013064947724343, "max": 3.964802847774427, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2293.9717294573784, "min": 237.66331184655428, "max": 2357.504774212837, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.907958653249367, "min": 1.9013064947724343, "max": 3.964802847774427, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2293.9717294573784, "min": 237.66331184655428, "max": 2357.504774212837, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018693126442505873, "min": 0.012085831308892618, "max": 0.018738718276532985, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05607937932751762, "min": 0.024171662617785236, "max": 0.05607937932751762, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.057050445054968195, "min": 0.020416574211170276, "max": 0.06387384614596764, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17115133516490458, "min": 0.04083314842234055, "max": 0.17845956832170487, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.764398745233331e-06, "min": 3.764398745233331e-06, "max": 0.000295363426545525, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1293196235699992e-05, "min": 1.1293196235699992e-05, "max": 0.0008442888185703997, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10125476666666666, "min": 0.10125476666666666, "max": 0.19845447500000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3037643, "min": 0.20767064999999996, "max": 0.5814296, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.261285666666666e-05, "min": 7.261285666666666e-05, "max": 0.0049228783025, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021783856999999996, "min": 0.00021783856999999996, "max": 0.014073337040000005, "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": "1727265819", "python_version": "3.10.12 (main, Sep 25 2024, 14:52:12) [GCC 13.2.0]", "command_line_arguments": "/home/itamar/PycharmProjects/huggyDog/.venv/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.4.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1727266955" }, "total": 1135.387264140998, "count": 1, "self": 0.16734554304275662, "children": { "run_training.setup": { "total": 0.009107159974519163, "count": 1, "self": 0.009107159974519163 }, "TrainerController.start_learning": { "total": 1135.2108114379807, "count": 1, "self": 2.3742618804681115, "children": { "TrainerController._reset_env": { "total": 0.7091515630017966, "count": 1, "self": 0.7091515630017966 }, "TrainerController.advance": { "total": 1132.0500402745092, "count": 232749, "self": 2.2274959626956843, "children": { "env_step": { "total": 836.9137288217898, "count": 232749, "self": 543.1624536960735, "children": { "SubprocessEnvManager._take_step": { "total": 292.2503198546474, "count": 232749, "self": 8.127176666399464, "children": { "TorchPolicy.evaluate": { "total": 284.1231431882479, "count": 222952, "self": 284.1231431882479 } } }, "workers": { "total": 1.5009552710689604, "count": 232749, "self": 0.0, "children": { "worker_root": { "total": 1132.3723742977018, "count": 232749, "is_parallel": true, "self": 714.7881266030599, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0003182539949193597, "count": 1, "is_parallel": true, "self": 8.054700447246432e-05, "children": { "_process_rank_one_or_two_observation": { "total": 0.00023770699044689536, "count": 2, "is_parallel": true, "self": 0.00023770699044689536 } } }, "UnityEnvironment.step": { "total": 0.010369614989031106, "count": 1, "is_parallel": true, "self": 9.572197450324893e-05, "children": { "UnityEnvironment._generate_step_input": { "total": 8.206901839002967e-05, "count": 1, "is_parallel": true, "self": 8.206901839002967e-05 }, "communicator.exchange": { "total": 0.009906312974635512, "count": 1, "is_parallel": true, "self": 0.009906312974635512 }, "steps_from_proto": { "total": 0.000285511021502316, "count": 1, "is_parallel": true, "self": 6.60790828987956e-05, "children": { "_process_rank_one_or_two_observation": { "total": 0.0002194319386035204, "count": 2, "is_parallel": true, "self": 0.0002194319386035204 } } } } } } }, "UnityEnvironment.step": { "total": 417.5842476946418, "count": 232748, "is_parallel": true, "self": 13.262501044606324, "children": { "UnityEnvironment._generate_step_input": { "total": 23.89304717705818, "count": 232748, "is_parallel": true, "self": 23.89304717705818 }, "communicator.exchange": { "total": 348.94716023636283, "count": 232748, "is_parallel": true, "self": 348.94716023636283 }, "steps_from_proto": { "total": 31.48153923661448, "count": 232748, "is_parallel": true, "self": 11.408410875184927, "children": { "_process_rank_one_or_two_observation": { "total": 20.073128361429553, "count": 465496, "is_parallel": true, "self": 20.073128361429553 } } } } } } } } } } }, "trainer_advance": { "total": 292.9088154900237, "count": 232749, "self": 3.2375654109637253, "children": { "process_trajectory": { "total": 119.6908002088312, "count": 232749, "self": 118.92354650481138, "children": { "RLTrainer._checkpoint": { "total": 0.7672537040198222, "count": 10, "self": 0.7672537040198222 } } }, "_update_policy": { "total": 169.98044987022877, "count": 97, "self": 132.48607529653236, "children": { "TorchPPOOptimizer.update": { "total": 37.494374573696405, "count": 2910, "self": 37.494374573696405 } } } } } } }, "trainer_threads": { "total": 6.00994098931551e-07, "count": 1, "self": 6.00994098931551e-07 }, "TrainerController._save_models": { "total": 0.07735711900750175, "count": 1, "self": 0.0007011810084804893, "children": { "RLTrainer._checkpoint": { "total": 0.07665593799902126, "count": 1, "self": 0.07665593799902126 } } } } } } }