{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.412527322769165, "min": 1.412527322769165, "max": 1.4286195039749146, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70504.890625, "min": 69039.0, "max": 76162.625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 86.61754385964912, "min": 82.87248322147651, "max": 399.0, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49372.0, "min": 48796.0, "max": 50249.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999952.0, "min": 49673.0, "max": 1999952.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999952.0, "min": 49673.0, "max": 1999952.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.417802333831787, "min": 0.03630182892084122, "max": 2.433789014816284, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1378.1473388671875, "min": 4.501426696777344, "max": 1381.04296875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8368468147620822, "min": 1.7603933972817274, "max": 3.951794030864316, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2187.0026844143867, "min": 218.2887812629342, "max": 2189.293893098831, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8368468147620822, "min": 1.7603933972817274, "max": 3.951794030864316, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2187.0026844143867, "min": 218.2887812629342, "max": 2189.293893098831, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017072539894757533, "min": 0.012367759072609865, "max": 0.01985546180876554, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0512176196842726, "min": 0.02473551814521973, "max": 0.057222999299907915, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05808950687448183, "min": 0.02323387327293555, "max": 0.060146518113712466, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1742685206234455, "min": 0.048964376933872705, "max": 0.1761999849230051, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.7964487345500032e-06, "min": 3.7964487345500032e-06, "max": 0.00029532292655902497, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.138934620365001e-05, "min": 1.138934620365001e-05, "max": 0.0008440440186519999, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10126544999999998, "min": 0.10126544999999998, "max": 0.19844097500000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30379634999999994, "min": 0.2077036, "max": 0.5813479999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.314595500000007e-05, "min": 7.314595500000007e-05, "max": 0.0049222046525, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002194378650000002, "min": 0.0002194378650000002, "max": 0.014069265200000004, "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": "1670680707", "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": "1670682958" }, "total": 2251.002594623, "count": 1, "self": 0.44284688500010816, "children": { "run_training.setup": { "total": 0.11971305800000209, "count": 1, "self": 0.11971305800000209 }, "TrainerController.start_learning": { "total": 2250.44003468, "count": 1, "self": 3.9290990220388267, "children": { "TrainerController._reset_env": { "total": 10.988467049000064, "count": 1, "self": 10.988467049000064 }, "TrainerController.advance": { "total": 2235.3918095999607, "count": 232005, "self": 4.044793448121254, "children": { "env_step": { "total": 1741.4256529628665, "count": 232005, "self": 1460.2780648927196, "children": { "SubprocessEnvManager._take_step": { "total": 278.4826052060573, "count": 232005, "self": 14.666893420998917, "children": { "TorchPolicy.evaluate": { "total": 263.8157117850584, "count": 222923, "self": 66.48538989407132, "children": { "TorchPolicy.sample_actions": { "total": 197.33032189098708, "count": 222923, "self": 197.33032189098708 } } } } }, "workers": { "total": 2.664982864089666, "count": 232005, "self": 0.0, "children": { "worker_root": { "total": 2242.776377656912, "count": 232005, "is_parallel": true, "self": 1045.8251354709325, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005006766000064999, "count": 1, "is_parallel": true, "self": 0.0003521530001080464, "children": { "_process_rank_one_or_two_observation": { "total": 0.004654612999956953, "count": 2, "is_parallel": true, "self": 0.004654612999956953 } } }, "UnityEnvironment.step": { "total": 0.02804875300000731, "count": 1, "is_parallel": true, "self": 0.0003007030001072053, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023332699993261485, "count": 1, "is_parallel": true, "self": 0.00023332699993261485 }, "communicator.exchange": { "total": 0.026760359999911998, "count": 1, "is_parallel": true, "self": 0.026760359999911998 }, "steps_from_proto": { "total": 0.0007543630000554913, "count": 1, "is_parallel": true, "self": 0.00026274000015291676, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004916229999025745, "count": 2, "is_parallel": true, "self": 0.0004916229999025745 } } } } } } }, "UnityEnvironment.step": { "total": 1196.9512421859793, "count": 232004, "is_parallel": true, "self": 35.33197642808136, "children": { "UnityEnvironment._generate_step_input": { "total": 75.66660132195625, "count": 232004, "is_parallel": true, "self": 75.66660132195625 }, "communicator.exchange": { "total": 991.9481841939524, "count": 232004, "is_parallel": true, "self": 991.9481841939524 }, "steps_from_proto": { "total": 94.00448024198909, "count": 232004, "is_parallel": true, "self": 38.51650048094132, "children": { "_process_rank_one_or_two_observation": { "total": 55.48797976104777, "count": 464008, "is_parallel": true, "self": 55.48797976104777 } } } } } } } } } } }, "trainer_advance": { "total": 489.9213631889728, "count": 232005, "self": 6.031210014979024, "children": { "process_trajectory": { "total": 150.1205823259936, "count": 232005, "self": 149.63221382299366, "children": { "RLTrainer._checkpoint": { "total": 0.48836850299994694, "count": 4, "self": 0.48836850299994694 } } }, "_update_policy": { "total": 333.76957084800017, "count": 97, "self": 278.9866704039913, "children": { "TorchPPOOptimizer.update": { "total": 54.782900444008874, "count": 2910, "self": 54.782900444008874 } } } } } } }, "trainer_threads": { "total": 8.760002856433857e-07, "count": 1, "self": 8.760002856433857e-07 }, "TrainerController._save_models": { "total": 0.13065813299999718, "count": 1, "self": 0.002744568999787589, "children": { "RLTrainer._checkpoint": { "total": 0.1279135640002096, "count": 1, "self": 0.1279135640002096 } } } } } } }