{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4050509929656982, "min": 1.4050509929656982, "max": 1.4293718338012695, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68234.8984375, "min": 68234.8984375, "max": 77395.1484375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 89.9872495446266, "min": 87.08098591549296, "max": 402.256, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49403.0, "min": 48742.0, "max": 50282.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999962.0, "min": 49657.0, "max": 1999962.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999962.0, "min": 49657.0, "max": 1999962.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3792378902435303, "min": 0.2200859934091568, "max": 2.3894219398498535, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1306.20166015625, "min": 27.29066276550293, "max": 1355.202392578125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7383412754600815, "min": 1.7880733068431578, "max": 3.891004576042236, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2052.349360227585, "min": 221.72109004855156, "max": 2112.712162077427, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7383412754600815, "min": 1.7880733068431578, "max": 3.891004576042236, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2052.349360227585, "min": 221.72109004855156, "max": 2112.712162077427, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016408212295371212, "min": 0.014243003730371129, "max": 0.02157630574850676, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.049224636886113636, "min": 0.028486007460742258, "max": 0.05823503900513363, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05670246324605412, "min": 0.01933111942683657, "max": 0.05704000939925512, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17010738973816236, "min": 0.03866223885367314, "max": 0.17074640281498432, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.162248945949996e-06, "min": 3.162248945949996e-06, "max": 0.00029538075153974996, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.486746837849988e-06, "min": 9.486746837849988e-06, "max": 0.0008442414185862, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10105405000000002, "min": 0.10105405000000002, "max": 0.19846025, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3031621500000001, "min": 0.2072719, "max": 0.5814138, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.259709499999994e-05, "min": 6.259709499999994e-05, "max": 0.004923166475000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00018779128499999984, "min": 0.00018779128499999984, "max": 0.01407254862, "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": "1700787642", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700790032" }, "total": 2389.6837751269995, "count": 1, "self": 0.4302726119994986, "children": { "run_training.setup": { "total": 0.04547325099997579, "count": 1, "self": 0.04547325099997579 }, "TrainerController.start_learning": { "total": 2389.2080292640003, "count": 1, "self": 4.338771037060724, "children": { "TrainerController._reset_env": { "total": 9.978757906999931, "count": 1, "self": 9.978757906999931 }, "TrainerController.advance": { "total": 2374.7896913359396, "count": 231616, "self": 4.401649486960196, "children": { "env_step": { "total": 1880.634451381933, "count": 231616, "self": 1548.5167556069941, "children": { "SubprocessEnvManager._take_step": { "total": 329.3381926130114, "count": 231616, "self": 16.96916861700845, "children": { "TorchPolicy.evaluate": { "total": 312.36902399600297, "count": 222840, "self": 312.36902399600297 } } }, "workers": { "total": 2.7795031619276642, "count": 231616, "self": 0.0, "children": { "worker_root": { "total": 2381.662127058003, "count": 231616, "is_parallel": true, "self": 1122.0999318299682, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001018643000065822, "count": 1, "is_parallel": true, "self": 0.0002894289999630928, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007292140001027292, "count": 2, "is_parallel": true, "self": 0.0007292140001027292 } } }, "UnityEnvironment.step": { "total": 0.027936513999975432, "count": 1, "is_parallel": true, "self": 0.0002892010001005474, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001855549999163486, "count": 1, "is_parallel": true, "self": 0.0001855549999163486 }, "communicator.exchange": { "total": 0.026734654999927443, "count": 1, "is_parallel": true, "self": 0.026734654999927443 }, "steps_from_proto": { "total": 0.000727103000031093, "count": 1, "is_parallel": true, "self": 0.0002365320000308202, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004905710000002728, "count": 2, "is_parallel": true, "self": 0.0004905710000002728 } } } } } } }, "UnityEnvironment.step": { "total": 1259.5621952280349, "count": 231615, "is_parallel": true, "self": 39.42246499220141, "children": { "UnityEnvironment._generate_step_input": { "total": 81.4933772419696, "count": 231615, "is_parallel": true, "self": 81.4933772419696 }, "communicator.exchange": { "total": 1051.2868346679256, "count": 231615, "is_parallel": true, "self": 1051.2868346679256 }, "steps_from_proto": { "total": 87.35951832593832, "count": 231615, "is_parallel": true, "self": 30.355912803734327, "children": { "_process_rank_one_or_two_observation": { "total": 57.003605522204, "count": 463230, "is_parallel": true, "self": 57.003605522204 } } } } } } } } } } }, "trainer_advance": { "total": 489.75359046704614, "count": 231616, "self": 6.428872520968639, "children": { "process_trajectory": { "total": 149.80996875407698, "count": 231616, "self": 148.61692881607735, "children": { "RLTrainer._checkpoint": { "total": 1.1930399379996288, "count": 10, "self": 1.1930399379996288 } } }, "_update_policy": { "total": 333.5147491920005, "count": 97, "self": 271.52953504600384, "children": { "TorchPPOOptimizer.update": { "total": 61.98521414599668, "count": 2910, "self": 61.98521414599668 } } } } } } }, "trainer_threads": { "total": 1.1070001164625864e-06, "count": 1, "self": 1.1070001164625864e-06 }, "TrainerController._save_models": { "total": 0.10080787700007932, "count": 1, "self": 0.002142450000064855, "children": { "RLTrainer._checkpoint": { "total": 0.09866542700001446, "count": 1, "self": 0.09866542700001446 } } } } } } }