{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4082129001617432, "min": 1.4082129001617432, "max": 1.4291261434555054, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71371.046875, "min": 69300.125, "max": 76253.6640625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 98.95409181636727, "min": 87.47610619469026, "max": 390.3203125, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49576.0, "min": 48866.0, "max": 50177.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999474.0, "min": 49825.0, "max": 1999474.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999474.0, "min": 49825.0, "max": 1999474.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3507883548736572, "min": 0.031364452093839645, "max": 2.435443639755249, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1180.095703125, "min": 3.983285427093506, "max": 1343.17822265625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5545885409729414, "min": 1.856823153148486, "max": 4.00661034479794, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1784.4034475684166, "min": 235.8165404498577, "max": 2107.477041363716, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5545885409729414, "min": 1.856823153148486, "max": 4.00661034479794, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1784.4034475684166, "min": 235.8165404498577, "max": 2107.477041363716, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01309355038449414, "min": 0.01309355038449414, "max": 0.020819643248493475, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03928065115348242, "min": 0.02776997757367402, "max": 0.05938962733489461, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.056385114085343156, "min": 0.02281155015031497, "max": 0.06061395841340224, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16915534225602946, "min": 0.04562310030062994, "max": 0.16946651885906855, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.5793988069000078e-06, "min": 3.5793988069000078e-06, "max": 0.00029531160156279993, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0738196420700024e-05, "min": 1.0738196420700024e-05, "max": 0.0008441433186189, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10119310000000002, "min": 0.10119310000000002, "max": 0.19843719999999998, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30357930000000005, "min": 0.20757015, "max": 0.5813811, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.953569000000013e-05, "min": 6.953569000000013e-05, "max": 0.004922016279999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002086070700000004, "min": 0.0002086070700000004, "max": 0.014070916889999998, "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": "1677950363", "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": "1677952860" }, "total": 2496.601962099, "count": 1, "self": 0.4394619730001068, "children": { "run_training.setup": { "total": 0.10729066900000817, "count": 1, "self": 0.10729066900000817 }, "TrainerController.start_learning": { "total": 2496.055209457, "count": 1, "self": 4.642080394066397, "children": { "TrainerController._reset_env": { "total": 10.068002261000004, "count": 1, "self": 10.068002261000004 }, "TrainerController.advance": { "total": 2481.231852810933, "count": 232180, "self": 4.680931108039658, "children": { "env_step": { "total": 1944.6610740329838, "count": 232180, "self": 1628.2733638119698, "children": { "SubprocessEnvManager._take_step": { "total": 313.3882499590564, "count": 232180, "self": 16.806932282036087, "children": { "TorchPolicy.evaluate": { "total": 296.5813176770203, "count": 223034, "self": 74.55629210304346, "children": { "TorchPolicy.sample_actions": { "total": 222.02502557397685, "count": 223034, "self": 222.02502557397685 } } } } }, "workers": { "total": 2.999460261957722, "count": 232180, "self": 0.0, "children": { "worker_root": { "total": 2487.004930325999, "count": 232180, "is_parallel": true, "self": 1171.3629595280352, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010925530000349681, "count": 1, "is_parallel": true, "self": 0.00034714900004928495, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007454039999856832, "count": 2, "is_parallel": true, "self": 0.0007454039999856832 } } }, "UnityEnvironment.step": { "total": 0.03139220399998521, "count": 1, "is_parallel": true, "self": 0.0003083609999521286, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002218640000251071, "count": 1, "is_parallel": true, "self": 0.0002218640000251071 }, "communicator.exchange": { "total": 0.027937850999990133, "count": 1, "is_parallel": true, "self": 0.027937850999990133 }, "steps_from_proto": { "total": 0.002924128000017845, "count": 1, "is_parallel": true, "self": 0.0002935800000045674, "children": { "_process_rank_one_or_two_observation": { "total": 0.0026305480000132775, "count": 2, "is_parallel": true, "self": 0.0026305480000132775 } } } } } } }, "UnityEnvironment.step": { "total": 1315.6419707979637, "count": 232179, "is_parallel": true, "self": 39.005549074831606, "children": { "UnityEnvironment._generate_step_input": { "total": 83.19513040604289, "count": 232179, "is_parallel": true, "self": 83.19513040604289 }, "communicator.exchange": { "total": 1099.6440867190527, "count": 232179, "is_parallel": true, "self": 1099.6440867190527 }, "steps_from_proto": { "total": 93.7972045980365, "count": 232179, "is_parallel": true, "self": 39.95259874904582, "children": { "_process_rank_one_or_two_observation": { "total": 53.84460584899068, "count": 464358, "is_parallel": true, "self": 53.84460584899068 } } } } } } } } } } }, "trainer_advance": { "total": 531.8898476699095, "count": 232180, "self": 7.131257833973564, "children": { "process_trajectory": { "total": 169.8729961479367, "count": 232180, "self": 168.63438251993733, "children": { "RLTrainer._checkpoint": { "total": 1.2386136279993707, "count": 10, "self": 1.2386136279993707 } } }, "_update_policy": { "total": 354.8855936879993, "count": 97, "self": 297.11033668099213, "children": { "TorchPPOOptimizer.update": { "total": 57.775257007007156, "count": 2910, "self": 57.775257007007156 } } } } } } }, "trainer_threads": { "total": 8.340002750628628e-07, "count": 1, "self": 8.340002750628628e-07 }, "TrainerController._save_models": { "total": 0.11327315700009422, "count": 1, "self": 0.0023279140000340703, "children": { "RLTrainer._checkpoint": { "total": 0.11094524300006015, "count": 1, "self": 0.11094524300006015 } } } } } } }