{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4074468612670898, "min": 1.4074468612670898, "max": 1.4294682741165161, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69253.421875, "min": 68813.125, "max": 75960.4296875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 107.36129032258064, "min": 91.4765478424015, "max": 392.171875, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49923.0, "min": 48757.0, "max": 50198.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999685.0, "min": 49657.0, "max": 1999685.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999685.0, "min": 49657.0, "max": 1999685.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3350555896759033, "min": 0.11603789031505585, "max": 2.429384469985962, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1085.8009033203125, "min": 14.736811637878418, "max": 1274.8837890625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5701126606233657, "min": 1.9363990472996329, "max": 3.993634290440114, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1660.102387189865, "min": 245.92267900705338, "max": 2060.044282376766, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5701126606233657, "min": 1.9363990472996329, "max": 3.993634290440114, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1660.102387189865, "min": 245.92267900705338, "max": 2060.044282376766, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.019899788561451717, "min": 0.012092343162415394, "max": 0.019899788561451717, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.059699365684355146, "min": 0.024184686324830788, "max": 0.059699365684355146, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05081704734928078, "min": 0.02381539347892006, "max": 0.05740688306589921, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15245114204784235, "min": 0.04763078695784012, "max": 0.1682766892015934, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.140548953183327e-06, "min": 3.140548953183327e-06, "max": 0.00029535795154735, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.42164685954998e-06, "min": 9.42164685954998e-06, "max": 0.0008439154686948498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10104681666666666, "min": 0.10104681666666666, "max": 0.19845265000000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30314045, "min": 0.20724365000000006, "max": 0.5813051500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.223615166666656e-05, "min": 6.223615166666656e-05, "max": 0.004922787235, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001867084549999997, "min": 0.0001867084549999997, "max": 0.014067126984999994, "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": "1677732648", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1677734956" }, "total": 2307.776167504, "count": 1, "self": 0.450617948999934, "children": { "run_training.setup": { "total": 0.11193260199991073, "count": 1, "self": 0.11193260199991073 }, "TrainerController.start_learning": { "total": 2307.2136169530004, "count": 1, "self": 4.010851941986857, "children": { "TrainerController._reset_env": { "total": 10.376088736000042, "count": 1, "self": 10.376088736000042 }, "TrainerController.advance": { "total": 2292.7078388380132, "count": 231686, "self": 4.408664945967757, "children": { "env_step": { "total": 1778.6355373150122, "count": 231686, "self": 1481.2987459320493, "children": { "SubprocessEnvManager._take_step": { "total": 294.6718787889373, "count": 231686, "self": 15.760804773973405, "children": { "TorchPolicy.evaluate": { "total": 278.9110740149639, "count": 222993, "self": 70.62934302602844, "children": { "TorchPolicy.sample_actions": { "total": 208.28173098893546, "count": 222993, "self": 208.28173098893546 } } } } }, "workers": { "total": 2.6649125940256226, "count": 231686, "self": 0.0, "children": { "worker_root": { "total": 2299.116632829971, "count": 231686, "is_parallel": true, "self": 1098.5859638759543, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003967308000028424, "count": 1, "is_parallel": true, "self": 0.000476432000141358, "children": { "_process_rank_one_or_two_observation": { "total": 0.0034908759998870664, "count": 2, "is_parallel": true, "self": 0.0034908759998870664 } } }, "UnityEnvironment.step": { "total": 0.03607859600003849, "count": 1, "is_parallel": true, "self": 0.0002787510001098781, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019128300004922494, "count": 1, "is_parallel": true, "self": 0.00019128300004922494 }, "communicator.exchange": { "total": 0.03470767499993599, "count": 1, "is_parallel": true, "self": 0.03470767499993599 }, "steps_from_proto": { "total": 0.0009008869999433955, "count": 1, "is_parallel": true, "self": 0.0002525640001067586, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006483229998366369, "count": 2, "is_parallel": true, "self": 0.0006483229998366369 } } } } } } }, "UnityEnvironment.step": { "total": 1200.5306689540166, "count": 231685, "is_parallel": true, "self": 37.54571808212859, "children": { "UnityEnvironment._generate_step_input": { "total": 77.38620038400325, "count": 231685, "is_parallel": true, "self": 77.38620038400325 }, "communicator.exchange": { "total": 997.0366909189427, "count": 231685, "is_parallel": true, "self": 997.0366909189427 }, "steps_from_proto": { "total": 88.56205956894189, "count": 231685, "is_parallel": true, "self": 35.42936807900003, "children": { "_process_rank_one_or_two_observation": { "total": 53.13269148994186, "count": 463370, "is_parallel": true, "self": 53.13269148994186 } } } } } } } } } } }, "trainer_advance": { "total": 509.66363657703323, "count": 231686, "self": 6.649952219987085, "children": { "process_trajectory": { "total": 158.88052922504676, "count": 231686, "self": 156.21581512804698, "children": { "RLTrainer._checkpoint": { "total": 2.6647140969997736, "count": 20, "self": 2.6647140969997736 } } }, "_update_policy": { "total": 344.1331551319994, "count": 97, "self": 286.5149807020109, "children": { "TorchPPOOptimizer.update": { "total": 57.61817442998847, "count": 2910, "self": 57.61817442998847 } } } } } } }, "trainer_threads": { "total": 8.330002856382634e-07, "count": 1, "self": 8.330002856382634e-07 }, "TrainerController._save_models": { "total": 0.11883660400008011, "count": 1, "self": 0.002160137000373652, "children": { "RLTrainer._checkpoint": { "total": 0.11667646699970646, "count": 1, "self": 0.11667646699970646 } } } } } } }