{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4082883596420288, "min": 1.4082883596420288, "max": 1.4294209480285645, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70018.6875, "min": 68676.3984375, "max": 78101.5625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 80.75331125827815, "min": 79.73409461663948, "max": 416.73333333333335, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48775.0, "min": 48775.0, "max": 50073.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999893.0, "min": 49933.0, "max": 1999893.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999893.0, "min": 49933.0, "max": 1999893.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.428748369216919, "min": 0.15868766605854034, "max": 2.4964287281036377, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1469.3927001953125, "min": 18.883832931518555, "max": 1489.3580322265625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7641025839758315, "min": 1.9671844662237568, "max": 3.9852593558585583, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2277.282063305378, "min": 234.09495148062706, "max": 2373.6676456928253, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7641025839758315, "min": 1.9671844662237568, "max": 3.9852593558585583, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2277.282063305378, "min": 234.09495148062706, "max": 2373.6676456928253, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016384675966886184, "min": 0.014069039110230126, "max": 0.020698974431272492, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04915402790065855, "min": 0.02813807822046025, "max": 0.062096923293817476, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05867650289502408, "min": 0.021907517313957216, "max": 0.06006228944493664, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17602950868507225, "min": 0.04381503462791443, "max": 0.18018686833480993, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.417748860783327e-06, "min": 3.417748860783327e-06, "max": 0.000295280026573325, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.025324658234998e-05, "min": 1.025324658234998e-05, "max": 0.0008440558686480498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10113921666666666, "min": 0.10113921666666666, "max": 0.19842667500000008, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30341765, "min": 0.20744849999999998, "max": 0.5813519500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.684691166666659e-05, "min": 6.684691166666659e-05, "max": 0.004921491082500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020054073499999975, "min": 0.00020054073499999975, "max": 0.014069462304999999, "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": "1679063123", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1679065744" }, "total": 2621.189996921, "count": 1, "self": 0.4385423609996906, "children": { "run_training.setup": { "total": 0.10561558799997783, "count": 1, "self": 0.10561558799997783 }, "TrainerController.start_learning": { "total": 2620.645838972, "count": 1, "self": 5.215711525020652, "children": { "TrainerController._reset_env": { "total": 9.467718013000024, "count": 1, "self": 9.467718013000024 }, "TrainerController.advance": { "total": 2605.839476828979, "count": 232619, "self": 5.4160920320268815, "children": { "env_step": { "total": 2047.7415257999605, "count": 232619, "self": 1721.4676617658388, "children": { "SubprocessEnvManager._take_step": { "total": 322.7379343170527, "count": 232619, "self": 19.117341302070884, "children": { "TorchPolicy.evaluate": { "total": 303.6205930149818, "count": 222998, "self": 303.6205930149818 } } }, "workers": { "total": 3.5359297170691093, "count": 232619, "self": 0.0, "children": { "worker_root": { "total": 2611.254902613899, "count": 232619, "is_parallel": true, "self": 1213.1120538628984, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000968035999960648, "count": 1, "is_parallel": true, "self": 0.00025322499999447246, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007148109999661756, "count": 2, "is_parallel": true, "self": 0.0007148109999661756 } } }, "UnityEnvironment.step": { "total": 0.03143435900000213, "count": 1, "is_parallel": true, "self": 0.0003396569999836174, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002188810000234298, "count": 1, "is_parallel": true, "self": 0.0002188810000234298 }, "communicator.exchange": { "total": 0.030132176999984495, "count": 1, "is_parallel": true, "self": 0.030132176999984495 }, "steps_from_proto": { "total": 0.0007436440000105904, "count": 1, "is_parallel": true, "self": 0.00025382299998000235, "children": { "_process_rank_one_or_two_observation": { "total": 0.000489821000030588, "count": 2, "is_parallel": true, "self": 0.000489821000030588 } } } } } } }, "UnityEnvironment.step": { "total": 1398.1428487510007, "count": 232618, "is_parallel": true, "self": 42.62704021476725, "children": { "UnityEnvironment._generate_step_input": { "total": 80.79793383114207, "count": 232618, "is_parallel": true, "self": 80.79793383114207 }, "communicator.exchange": { "total": 1176.7222458300475, "count": 232618, "is_parallel": true, "self": 1176.7222458300475 }, "steps_from_proto": { "total": 97.99562887504379, "count": 232618, "is_parallel": true, "self": 35.71597301807395, "children": { "_process_rank_one_or_two_observation": { "total": 62.27965585696984, "count": 465236, "is_parallel": true, "self": 62.27965585696984 } } } } } } } } } } }, "trainer_advance": { "total": 552.6818589969917, "count": 232619, "self": 8.177253275985436, "children": { "process_trajectory": { "total": 151.28037937400876, "count": 232619, "self": 149.80984994400825, "children": { "RLTrainer._checkpoint": { "total": 1.4705294300005107, "count": 10, "self": 1.4705294300005107 } } }, "_update_policy": { "total": 393.22422634699745, "count": 97, "self": 330.9416436960021, "children": { "TorchPPOOptimizer.update": { "total": 62.28258265099538, "count": 2910, "self": 62.28258265099538 } } } } } } }, "trainer_threads": { "total": 1.0190001376031432e-06, "count": 1, "self": 1.0190001376031432e-06 }, "TrainerController._save_models": { "total": 0.12293158600004972, "count": 1, "self": 0.0021474209997904836, "children": { "RLTrainer._checkpoint": { "total": 0.12078416500025924, "count": 1, "self": 0.12078416500025924 } } } } } } }