{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4021071195602417, "min": 1.4021071195602417, "max": 1.4285624027252197, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70715.2734375, "min": 68755.796875, "max": 78291.6171875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 77.38244514106583, "min": 77.38244514106583, "max": 398.0472440944882, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49370.0, "min": 49223.0, "max": 50552.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999953.0, "min": 49929.0, "max": 1999953.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999953.0, "min": 49929.0, "max": 1999953.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.434037446975708, "min": 0.18068905174732208, "max": 2.444122552871704, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1552.9158935546875, "min": 22.766820907592773, "max": 1552.9158935546875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.831139999777546, "min": 1.774592774136672, "max": 3.8980545167518335, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2444.267319858074, "min": 223.59868954122066, "max": 2444.267319858074, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.831139999777546, "min": 1.774592774136672, "max": 3.8980545167518335, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2444.267319858074, "min": 223.59868954122066, "max": 2444.267319858074, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01733175299628379, "min": 0.014876366295478269, "max": 0.020073180988644405, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05199525898885137, "min": 0.029752732590956538, "max": 0.05743840227374998, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.0577375476145082, "min": 0.020407349554200968, "max": 0.05860588811337948, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1732126428435246, "min": 0.040814699108401936, "max": 0.1732126428435246, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.615198794966661e-06, "min": 3.615198794966661e-06, "max": 0.000295302526565825, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0845596384899983e-05, "min": 1.0845596384899983e-05, "max": 0.0008439241686919499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10120503333333335, "min": 0.10120503333333335, "max": 0.19843417500000005, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3036151, "min": 0.20754545000000002, "max": 0.58130805, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.013116333333322e-05, "min": 7.013116333333322e-05, "max": 0.004921865332500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021039348999999966, "min": 0.00021039348999999966, "max": 0.014067271695000001, "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": "1709246337", "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=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1709249024" }, "total": 2687.72515999, "count": 1, "self": 0.48762359699958324, "children": { "run_training.setup": { "total": 0.05035871400002634, "count": 1, "self": 0.05035871400002634 }, "TrainerController.start_learning": { "total": 2687.1871776790003, "count": 1, "self": 5.131489091063486, "children": { "TrainerController._reset_env": { "total": 3.389206181000077, "count": 1, "self": 3.389206181000077 }, "TrainerController.advance": { "total": 2678.544136387937, "count": 232724, "self": 5.480063650960801, "children": { "env_step": { "total": 2158.9604445430195, "count": 232724, "self": 1784.9942308570207, "children": { "SubprocessEnvManager._take_step": { "total": 370.51416983404647, "count": 232724, "self": 19.126779938050618, "children": { "TorchPolicy.evaluate": { "total": 351.38738989599585, "count": 222946, "self": 351.38738989599585 } } }, "workers": { "total": 3.4520438519523395, "count": 232724, "self": 0.0, "children": { "worker_root": { "total": 2678.7032265898806, "count": 232724, "is_parallel": true, "self": 1231.2177996490182, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001008365999950911, "count": 1, "is_parallel": true, "self": 0.0002862219999997251, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007221439999511858, "count": 2, "is_parallel": true, "self": 0.0007221439999511858 } } }, "UnityEnvironment.step": { "total": 0.07392906699999457, "count": 1, "is_parallel": true, "self": 0.0004166240000813559, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0001950779999333463, "count": 1, "is_parallel": true, "self": 0.0001950779999333463 }, "communicator.exchange": { "total": 0.07258555500004604, "count": 1, "is_parallel": true, "self": 0.07258555500004604 }, "steps_from_proto": { "total": 0.0007318099999338301, "count": 1, "is_parallel": true, "self": 0.0001762969999390407, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005555129999947894, "count": 2, "is_parallel": true, "self": 0.0005555129999947894 } } } } } } }, "UnityEnvironment.step": { "total": 1447.4854269408625, "count": 232723, "is_parallel": true, "self": 45.50239196190023, "children": { "UnityEnvironment._generate_step_input": { "total": 97.05961078190569, "count": 232723, "is_parallel": true, "self": 97.05961078190569 }, "communicator.exchange": { "total": 1201.0119397000485, "count": 232723, "is_parallel": true, "self": 1201.0119397000485 }, "steps_from_proto": { "total": 103.91148449700825, "count": 232723, "is_parallel": true, "self": 38.70225483096647, "children": { "_process_rank_one_or_two_observation": { "total": 65.20922966604178, "count": 465446, "is_parallel": true, "self": 65.20922966604178 } } } } } } } } } } }, "trainer_advance": { "total": 514.1036281939566, "count": 232724, "self": 7.58230190985978, "children": { "process_trajectory": { "total": 174.6344468510963, "count": 232724, "self": 173.15294409209628, "children": { "RLTrainer._checkpoint": { "total": 1.4815027590000227, "count": 10, "self": 1.4815027590000227 } } }, "_update_policy": { "total": 331.88687943300056, "count": 97, "self": 266.4856206340053, "children": { "TorchPPOOptimizer.update": { "total": 65.40125879899529, "count": 2910, "self": 65.40125879899529 } } } } } } }, "trainer_threads": { "total": 1.0129997463081963e-06, "count": 1, "self": 1.0129997463081963e-06 }, "TrainerController._save_models": { "total": 0.12234500599970488, "count": 1, "self": 0.002037790999565914, "children": { "RLTrainer._checkpoint": { "total": 0.12030721500013897, "count": 1, "self": 0.12030721500013897 } } } } } } }