{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.408209204673767, "min": 1.408209204673767, "max": 1.431309461593628, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70221.7578125, "min": 69030.71875, "max": 77621.0, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 82.37061769616027, "min": 74.52359208523592, "max": 430.2931034482759, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49340.0, "min": 48962.0, "max": 50116.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999934.0, "min": 49802.0, "max": 1999934.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999934.0, "min": 49802.0, "max": 1999934.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.5106725692749023, "min": -0.012750719673931599, "max": 2.5106725692749023, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1503.892822265625, "min": -1.4663327932357788, "max": 1602.45166015625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.90641967392525, "min": 1.809613637820534, "max": 4.017605984766866, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2339.945384681225, "min": 208.10556834936142, "max": 2531.5361217856407, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.90641967392525, "min": 1.809613637820534, "max": 4.017605984766866, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2339.945384681225, "min": 208.10556834936142, "max": 2531.5361217856407, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017980190358745554, "min": 0.014382259390873111, "max": 0.020250299421604723, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05394057107623666, "min": 0.028915221253798036, "max": 0.055579205780910954, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.055651591014530925, "min": 0.023178754809002083, "max": 0.060138056861857574, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16695477304359277, "min": 0.04635750961800417, "max": 0.17706339011589686, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.7029987657000084e-06, "min": 3.7029987657000084e-06, "max": 0.000295365826544725, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1108996297100026e-05, "min": 1.1108996297100026e-05, "max": 0.00084414466861845, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10123430000000004, "min": 0.10123430000000004, "max": 0.19845527499999993, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3037029000000001, "min": 0.20763275000000003, "max": 0.5813815500000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.159157000000017e-05, "min": 7.159157000000017e-05, "max": 0.0049229182224999985, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002147747100000005, "min": 0.0002147747100000005, "max": 0.014070939344999998, "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": "1698325495", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/home/alkzzz/miniconda3/envs/deep-rl-course/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+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1698328441" }, "total": 2945.268427713001, "count": 1, "self": 8.753030097997907, "children": { "run_training.setup": { "total": 0.016080008001154056, "count": 1, "self": 0.016080008001154056 }, "TrainerController.start_learning": { "total": 2936.499317607002, "count": 1, "self": 6.10664732924306, "children": { "TrainerController._reset_env": { "total": 2.8900734790004208, "count": 1, "self": 2.8900734790004208 }, "TrainerController.advance": { "total": 2927.3311014987576, "count": 233148, "self": 5.569325785072579, "children": { "env_step": { "total": 2429.5292370743737, "count": 233148, "self": 1659.549841642458, "children": { "SubprocessEnvManager._take_step": { "total": 765.8341022116183, "count": 233148, "self": 25.00594644087687, "children": { "TorchPolicy.evaluate": { "total": 740.8281557707414, "count": 222952, "self": 740.8281557707414 } } }, "workers": { "total": 4.14529322029739, "count": 233148, "self": 0.0, "children": { "worker_root": { "total": 2923.6755322195822, "count": 233148, "is_parallel": true, "self": 1594.2388597706667, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009563270014041336, "count": 1, "is_parallel": true, "self": 0.00025970400201913435, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006966229993849993, "count": 2, "is_parallel": true, "self": 0.0006966229993849993 } } }, "UnityEnvironment.step": { "total": 0.021546903999478673, "count": 1, "is_parallel": true, "self": 0.00020517899793048855, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00011633099893515464, "count": 1, "is_parallel": true, "self": 0.00011633099893515464 }, "communicator.exchange": { "total": 0.020733619001475745, "count": 1, "is_parallel": true, "self": 0.020733619001475745 }, "steps_from_proto": { "total": 0.0004917750011372846, "count": 1, "is_parallel": true, "self": 0.00013980599942442495, "children": { "_process_rank_one_or_two_observation": { "total": 0.0003519690017128596, "count": 2, "is_parallel": true, "self": 0.0003519690017128596 } } } } } } }, "UnityEnvironment.step": { "total": 1329.4366724489155, "count": 233147, "is_parallel": true, "self": 33.886713670699464, "children": { "UnityEnvironment._generate_step_input": { "total": 55.73984621931413, "count": 233147, "is_parallel": true, "self": 55.73984621931413 }, "communicator.exchange": { "total": 1169.1734764405992, "count": 233147, "is_parallel": true, "self": 1169.1734764405992 }, "steps_from_proto": { "total": 70.6366361183027, "count": 233147, "is_parallel": true, "self": 22.224105539748052, "children": { "_process_rank_one_or_two_observation": { "total": 48.41253057855465, "count": 466294, "is_parallel": true, "self": 48.41253057855465 } } } } } } } } } } }, "trainer_advance": { "total": 492.2325386393113, "count": 233148, "self": 10.37210736517045, "children": { "process_trajectory": { "total": 204.52305093412906, "count": 233148, "self": 203.22206928912965, "children": { "RLTrainer._checkpoint": { "total": 1.3009816449994105, "count": 10, "self": 1.3009816449994105 } } }, "_update_policy": { "total": 277.3373803400118, "count": 97, "self": 197.4295229090112, "children": { "TorchPPOOptimizer.update": { "total": 79.9078574310006, "count": 2910, "self": 79.9078574310006 } } } } } } }, "trainer_threads": { "total": 7.310009095817804e-07, "count": 1, "self": 7.310009095817804e-07 }, "TrainerController._save_models": { "total": 0.17149456900006044, "count": 1, "self": 0.0027427019995229784, "children": { "RLTrainer._checkpoint": { "total": 0.16875186700053746, "count": 1, "self": 0.16875186700053746 } } } } } } }