{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4078601598739624, "min": 1.4078601598739624, "max": 1.42777419090271, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70695.6953125, "min": 66910.359375, "max": 77059.171875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 69.60028248587571, "min": 69.60028248587571, "max": 411.0325203252033, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49277.0, "min": 49081.0, "max": 50557.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999987.0, "min": 49930.0, "max": 1999987.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999987.0, "min": 49930.0, "max": 1999987.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.5401904582977295, "min": -0.011418214067816734, "max": 2.5529625415802, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1798.454833984375, "min": -1.393022060394287, "max": 1798.454833984375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.927289384233076, "min": 1.7392089777305477, "max": 4.080068576643049, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2780.520884037018, "min": 212.18349528312683, "max": 2780.520884037018, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.927289384233076, "min": 1.7392089777305477, "max": 4.080068576643049, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2780.520884037018, "min": 212.18349528312683, "max": 2780.520884037018, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01693355693326642, "min": 0.013007153747215247, "max": 0.02081197634737085, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05080067079979926, "min": 0.026014307494430493, "max": 0.06243592904211255, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06670925762090418, "min": 0.0241774200151364, "max": 0.06795265755305688, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.20012777286271255, "min": 0.0483548400302728, "max": 0.20012777286271255, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4391988536333397e-06, "min": 3.4391988536333397e-06, "max": 0.00029534857655047497, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0317596560900019e-05, "min": 1.0317596560900019e-05, "max": 0.0008439594186801998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10114636666666665, "min": 0.10114636666666665, "max": 0.19844952500000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30343909999999996, "min": 0.20742564999999996, "max": 0.5813198, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.720369666666678e-05, "min": 6.720369666666678e-05, "max": 0.004922631297499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020161109000000032, "min": 0.00020161109000000032, "max": 0.014067858020000002, "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": "1706060197", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1706062780" }, "total": 2583.700815957, "count": 1, "self": 0.4998515289998977, "children": { "run_training.setup": { "total": 0.05475530900002923, "count": 1, "self": 0.05475530900002923 }, "TrainerController.start_learning": { "total": 2583.146209119, "count": 1, "self": 4.8295436489243, "children": { "TrainerController._reset_env": { "total": 4.228319763999934, "count": 1, "self": 4.228319763999934 }, "TrainerController.advance": { "total": 2573.958349319076, "count": 233270, "self": 5.100652566752615, "children": { "env_step": { "total": 2058.3174745401425, "count": 233270, "self": 1710.141343019087, "children": { "SubprocessEnvManager._take_step": { "total": 344.9911685151146, "count": 233270, "self": 18.6537640662591, "children": { "TorchPolicy.evaluate": { "total": 326.3374044488555, "count": 222957, "self": 326.3374044488555 } } }, "workers": { "total": 3.184963005940972, "count": 233270, "self": 0.0, "children": { "worker_root": { "total": 2575.3424759372806, "count": 233270, "is_parallel": true, "self": 1180.3985052913254, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000700088999565196, "count": 1, "is_parallel": true, "self": 0.0002178819995606318, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004822070000045642, "count": 2, "is_parallel": true, "self": 0.0004822070000045642 } } }, "UnityEnvironment.step": { "total": 0.056187351000062336, "count": 1, "is_parallel": true, "self": 0.0003818449999926088, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020638399973904598, "count": 1, "is_parallel": true, "self": 0.00020638399973904598 }, "communicator.exchange": { "total": 0.05478620000030787, "count": 1, "is_parallel": true, "self": 0.05478620000030787 }, "steps_from_proto": { "total": 0.0008129220000228088, "count": 1, "is_parallel": true, "self": 0.00019966200034104986, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006132599996817589, "count": 2, "is_parallel": true, "self": 0.0006132599996817589 } } } } } } }, "UnityEnvironment.step": { "total": 1394.9439706459552, "count": 233269, "is_parallel": true, "self": 44.299384496807306, "children": { "UnityEnvironment._generate_step_input": { "total": 88.95109263802624, "count": 233269, "is_parallel": true, "self": 88.95109263802624 }, "communicator.exchange": { "total": 1162.3760257330678, "count": 233269, "is_parallel": true, "self": 1162.3760257330678 }, "steps_from_proto": { "total": 99.31746777805392, "count": 233269, "is_parallel": true, "self": 34.941062600200894, "children": { "_process_rank_one_or_two_observation": { "total": 64.37640517785303, "count": 466538, "is_parallel": true, "self": 64.37640517785303 } } } } } } } } } } }, "trainer_advance": { "total": 510.5402222121811, "count": 233270, "self": 7.755655564013978, "children": { "process_trajectory": { "total": 167.04875217716472, "count": 233270, "self": 165.72610498216363, "children": { "RLTrainer._checkpoint": { "total": 1.3226471950010819, "count": 10, "self": 1.3226471950010819 } } }, "_update_policy": { "total": 335.7358144710024, "count": 97, "self": 270.0091195249938, "children": { "TorchPPOOptimizer.update": { "total": 65.72669494600859, "count": 2910, "self": 65.72669494600859 } } } } } } }, "trainer_threads": { "total": 9.089999366551638e-07, "count": 1, "self": 9.089999366551638e-07 }, "TrainerController._save_models": { "total": 0.12999547799972788, "count": 1, "self": 0.0022819789992354345, "children": { "RLTrainer._checkpoint": { "total": 0.12771349900049245, "count": 1, "self": 0.12771349900049245 } } } } } } }