{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4081602096557617, "min": 1.408150315284729, "max": 1.4285950660705566, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69939.09375, "min": 68798.7109375, "max": 77304.8671875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 101.7438524590164, "min": 93.06818181818181, "max": 386.1, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49651.0, "min": 48749.0, "max": 50287.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999424.0, "min": 49950.0, "max": 1999424.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999424.0, "min": 49950.0, "max": 1999424.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.377950668334961, "min": 0.06750226020812988, "max": 2.3934524059295654, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1160.43994140625, "min": 8.707791328430176, "max": 1233.154296875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7357824417899868, "min": 1.8107551519953928, "max": 3.8742848812572417, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1823.0618315935135, "min": 233.58741460740566, "max": 1942.0859763622284, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7357824417899868, "min": 1.8107551519953928, "max": 3.8742848812572417, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1823.0618315935135, "min": 233.58741460740566, "max": 1942.0859763622284, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015980038515044724, "min": 0.014069670617269972, "max": 0.021609088009184537, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03196007703008945, "min": 0.028139341234539945, "max": 0.06482726402755361, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.051560035720467565, "min": 0.02165054300179084, "max": 0.05354160128368272, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.10312007144093513, "min": 0.04330108600358168, "max": 0.16062480385104816, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.670648443149996e-06, "min": 4.670648443149996e-06, "max": 0.0002953387515537499, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.341296886299993e-06, "min": 9.341296886299993e-06, "max": 0.0008440584186472002, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10155684999999999, "min": 0.10155684999999999, "max": 0.19844625, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20311369999999998, "min": 0.20311369999999998, "max": 0.5813527999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.768681499999993e-05, "min": 8.768681499999993e-05, "max": 0.004922467875000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00017537362999999986, "min": 0.00017537362999999986, "max": 0.014069504720000004, "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": "1671300262", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "1.21.6", "end_time_seconds": "1671302373" }, "total": 2110.750398593, "count": 1, "self": 0.4419802460001847, "children": { "run_training.setup": { "total": 0.11871705099997598, "count": 1, "self": 0.11871705099997598 }, "TrainerController.start_learning": { "total": 2110.189701296, "count": 1, "self": 3.4987838670081146, "children": { "TrainerController._reset_env": { "total": 9.95163989699995, "count": 1, "self": 9.95163989699995 }, "TrainerController.advance": { "total": 2096.627402411992, "count": 231358, "self": 3.8835747148850714, "children": { "env_step": { "total": 1640.4895118780025, "count": 231358, "self": 1378.3247726579582, "children": { "SubprocessEnvManager._take_step": { "total": 259.7224414860081, "count": 231358, "self": 13.553269829048872, "children": { "TorchPolicy.evaluate": { "total": 246.16917165695924, "count": 222945, "self": 61.587878618931654, "children": { "TorchPolicy.sample_actions": { "total": 184.58129303802758, "count": 222945, "self": 184.58129303802758 } } } } }, "workers": { "total": 2.442297734036174, "count": 231358, "self": 0.0, "children": { "worker_root": { "total": 2102.879557760946, "count": 231358, "is_parallel": true, "self": 967.849282422892, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0022139690000244627, "count": 1, "is_parallel": true, "self": 0.0003957399999876543, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018182290000368084, "count": 2, "is_parallel": true, "self": 0.0018182290000368084 } } }, "UnityEnvironment.step": { "total": 0.02700681800001803, "count": 1, "is_parallel": true, "self": 0.00027393400000619295, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00018692700001565754, "count": 1, "is_parallel": true, "self": 0.00018692700001565754 }, "communicator.exchange": { "total": 0.025843560999987858, "count": 1, "is_parallel": true, "self": 0.025843560999987858 }, "steps_from_proto": { "total": 0.0007023960000083207, "count": 1, "is_parallel": true, "self": 0.00023107000004074507, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004713259999675756, "count": 2, "is_parallel": true, "self": 0.0004713259999675756 } } } } } } }, "UnityEnvironment.step": { "total": 1135.0302753380543, "count": 231357, "is_parallel": true, "self": 33.3889314250996, "children": { "UnityEnvironment._generate_step_input": { "total": 73.42353950294245, "count": 231357, "is_parallel": true, "self": 73.42353950294245 }, "communicator.exchange": { "total": 938.4232415720418, "count": 231357, "is_parallel": true, "self": 938.4232415720418 }, "steps_from_proto": { "total": 89.79456283797037, "count": 231357, "is_parallel": true, "self": 36.90371650390131, "children": { "_process_rank_one_or_two_observation": { "total": 52.89084633406907, "count": 462714, "is_parallel": true, "self": 52.89084633406907 } } } } } } } } } } }, "trainer_advance": { "total": 452.25431581910436, "count": 231358, "self": 5.784041259127605, "children": { "process_trajectory": { "total": 140.56082597897569, "count": 231358, "self": 139.40684302797604, "children": { "RLTrainer._checkpoint": { "total": 1.153982950999648, "count": 10, "self": 1.153982950999648 } } }, "_update_policy": { "total": 305.9094485810011, "count": 96, "self": 253.77001812900954, "children": { "TorchPPOOptimizer.update": { "total": 52.13943045199153, "count": 2880, "self": 52.13943045199153 } } } } } } }, "trainer_threads": { "total": 8.669999260746408e-07, "count": 1, "self": 8.669999260746408e-07 }, "TrainerController._save_models": { "total": 0.11187425299976894, "count": 1, "self": 0.0019101019997833646, "children": { "RLTrainer._checkpoint": { "total": 0.10996415099998558, "count": 1, "self": 0.10996415099998558 } } } } } } }