{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4095127582550049, "min": 1.4095127582550049, "max": 1.4310165643692017, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69022.4296875, "min": 68781.5546875, "max": 77850.875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 87.61061946902655, "min": 75.53211009174312, "max": 411.2439024390244, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49500.0, "min": 49147.0, "max": 50583.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999987.0, "min": 49956.0, "max": 1999987.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999987.0, "min": 49956.0, "max": 1999987.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.43117094039917, "min": 0.11754992604255676, "max": 2.5015475749969482, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1373.611572265625, "min": 14.34109115600586, "max": 1605.3106689453125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7989478752676367, "min": 1.827414137051731, "max": 3.9556461954676867, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2146.4055495262146, "min": 222.94452472031116, "max": 2545.707805931568, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7989478752676367, "min": 1.827414137051731, "max": 3.9556461954676867, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2146.4055495262146, "min": 222.94452472031116, "max": 2545.707805931568, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.019233426235021195, "min": 0.013193200546569035, "max": 0.020771261414241356, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.057700278705063585, "min": 0.02638640109313807, "max": 0.05947715070215054, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.053092293441295624, "min": 0.022148564302672945, "max": 0.06186031881305907, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15927688032388687, "min": 0.04429712860534589, "max": 0.1855809564391772, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6213987929000056e-06, "min": 3.6213987929000056e-06, "max": 0.00029532390155870004, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0864196378700017e-05, "min": 1.0864196378700017e-05, "max": 0.00084389056870315, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10120710000000001, "min": 0.10120710000000001, "max": 0.1984413, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30362130000000004, "min": 0.20757840000000002, "max": 0.5812968499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.02342900000001e-05, "min": 7.02342900000001e-05, "max": 0.004922220870000002, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021070287000000027, "min": 0.00021070287000000027, "max": 0.014066712815, "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": "1704099898", "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": "1704102436" }, "total": 2538.750571307, "count": 1, "self": 0.4409904229996755, "children": { "run_training.setup": { "total": 0.0518913399999974, "count": 1, "self": 0.0518913399999974 }, "TrainerController.start_learning": { "total": 2538.257689544, "count": 1, "self": 4.791068378000546, "children": { "TrainerController._reset_env": { "total": 3.290032201000031, "count": 1, "self": 3.290032201000031 }, "TrainerController.advance": { "total": 2530.0714647819996, "count": 232687, "self": 5.081524257037927, "children": { "env_step": { "total": 2007.3419268840212, "count": 232687, "self": 1671.0525883090218, "children": { "SubprocessEnvManager._take_step": { "total": 333.04213576606656, "count": 232687, "self": 17.236732959079347, "children": { "TorchPolicy.evaluate": { "total": 315.8054028069872, "count": 222935, "self": 315.8054028069872 } } }, "workers": { "total": 3.2472028089329683, "count": 232687, "self": 0.0, "children": { "worker_root": { "total": 2530.649130886077, "count": 232687, "is_parallel": true, "self": 1176.140989140012, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0006511269999691649, "count": 1, "is_parallel": true, "self": 0.0001931069999727697, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004580199999963952, "count": 2, "is_parallel": true, "self": 0.0004580199999963952 } } }, "UnityEnvironment.step": { "total": 0.04801111099999389, "count": 1, "is_parallel": true, "self": 0.00033754500003624344, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002079120000075818, "count": 1, "is_parallel": true, "self": 0.0002079120000075818 }, "communicator.exchange": { "total": 0.046711868999977924, "count": 1, "is_parallel": true, "self": 0.046711868999977924 }, "steps_from_proto": { "total": 0.0007537849999721402, "count": 1, "is_parallel": true, "self": 0.00019777299996803777, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005560120000041024, "count": 2, "is_parallel": true, "self": 0.0005560120000041024 } } } } } } }, "UnityEnvironment.step": { "total": 1354.508141746065, "count": 232686, "is_parallel": true, "self": 42.15950933720569, "children": { "UnityEnvironment._generate_step_input": { "total": 87.34823019592562, "count": 232686, "is_parallel": true, "self": 87.34823019592562 }, "communicator.exchange": { "total": 1129.4698418089301, "count": 232686, "is_parallel": true, "self": 1129.4698418089301 }, "steps_from_proto": { "total": 95.53056040400338, "count": 232686, "is_parallel": true, "self": 35.244261032065424, "children": { "_process_rank_one_or_two_observation": { "total": 60.28629937193796, "count": 465372, "is_parallel": true, "self": 60.28629937193796 } } } } } } } } } } }, "trainer_advance": { "total": 517.6480136409402, "count": 232687, "self": 7.036333191902941, "children": { "process_trajectory": { "total": 164.52310822203816, "count": 232687, "self": 163.30957905703798, "children": { "RLTrainer._checkpoint": { "total": 1.2135291650001818, "count": 10, "self": 1.2135291650001818 } } }, "_update_policy": { "total": 346.08857222699913, "count": 97, "self": 281.0661809449953, "children": { "TorchPPOOptimizer.update": { "total": 65.02239128200381, "count": 2910, "self": 65.02239128200381 } } } } } } }, "trainer_threads": { "total": 9.800000952964183e-07, "count": 1, "self": 9.800000952964183e-07 }, "TrainerController._save_models": { "total": 0.10512320299994826, "count": 1, "self": 0.0019106019999526325, "children": { "RLTrainer._checkpoint": { "total": 0.10321260099999563, "count": 1, "self": 0.10321260099999563 } } } } } } }