{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4090205430984497, "min": 1.4090205430984497, "max": 1.4288980960845947, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70336.8984375, "min": 69106.875, "max": 77800.0859375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 85.06551724137931, "min": 84.66380789022298, "max": 396.244094488189, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49338.0, "min": 48858.0, "max": 50323.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999932.0, "min": 49868.0, "max": 1999932.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999932.0, "min": 49868.0, "max": 1999932.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3656845092773438, "min": 0.19065605103969574, "max": 2.4591500759124756, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1372.0970458984375, "min": 24.022663116455078, "max": 1391.8194580078125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6786433417221596, "min": 1.9913737050124578, "max": 3.9373653899834777, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2133.6131381988525, "min": 250.91308683156967, "max": 2214.2372445464134, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6786433417221596, "min": 1.9913737050124578, "max": 3.9373653899834777, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2133.6131381988525, "min": 250.91308683156967, "max": 2214.2372445464134, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017963706068500566, "min": 0.013177558867027983, "max": 0.019900381929376938, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0538911182055017, "min": 0.026355117734055966, "max": 0.05937973916685829, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.057828951088918584, "min": 0.020810776234914858, "max": 0.0649347893272837, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17348685326675575, "min": 0.041621552469829716, "max": 0.17348685326675575, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.1990989336666635e-06, "min": 3.1990989336666635e-06, "max": 0.00029525190158269995, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.59729680099999e-06, "min": 9.59729680099999e-06, "max": 0.0008435047688317499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10106633333333331, "min": 0.10106633333333331, "max": 0.19841730000000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30319899999999994, "min": 0.20728289999999994, "max": 0.5811682499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.321003333333329e-05, "min": 6.321003333333329e-05, "max": 0.00492102327, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00018963009999999986, "min": 0.00018963009999999986, "max": 0.014060295675, "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": "1723129000", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1723131567" }, "total": 2566.392008751, "count": 1, "self": 0.43919195399985256, "children": { "run_training.setup": { "total": 0.06110564699997667, "count": 1, "self": 0.06110564699997667 }, "TrainerController.start_learning": { "total": 2565.89171115, "count": 1, "self": 4.655692809002176, "children": { "TrainerController._reset_env": { "total": 2.8081102490000376, "count": 1, "self": 2.8081102490000376 }, "TrainerController.advance": { "total": 2558.3028797119973, "count": 232124, "self": 5.0217358349600545, "children": { "env_step": { "total": 2047.6721557990031, "count": 232124, "self": 1683.4300232600572, "children": { "SubprocessEnvManager._take_step": { "total": 361.06037756997745, "count": 232124, "self": 18.415958877051253, "children": { "TorchPolicy.evaluate": { "total": 342.6444186929262, "count": 222982, "self": 342.6444186929262 } } }, "workers": { "total": 3.181754968968562, "count": 232124, "self": 0.0, "children": { "worker_root": { "total": 2558.237593478964, "count": 232124, "is_parallel": true, "self": 1202.8018644110289, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009550340000146207, "count": 1, "is_parallel": true, "self": 0.0002550290000158384, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007000049999987823, "count": 2, "is_parallel": true, "self": 0.0007000049999987823 } } }, "UnityEnvironment.step": { "total": 0.03139646400001084, "count": 1, "is_parallel": true, "self": 0.0003792909999447147, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004044870000257106, "count": 1, "is_parallel": true, "self": 0.0004044870000257106 }, "communicator.exchange": { "total": 0.02985961799998904, "count": 1, "is_parallel": true, "self": 0.02985961799998904 }, "steps_from_proto": { "total": 0.0007530680000513712, "count": 1, "is_parallel": true, "self": 0.00022807200002716854, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005249960000242027, "count": 2, "is_parallel": true, "self": 0.0005249960000242027 } } } } } } }, "UnityEnvironment.step": { "total": 1355.435729067935, "count": 232123, "is_parallel": true, "self": 40.61517104509471, "children": { "UnityEnvironment._generate_step_input": { "total": 89.88829578889658, "count": 232123, "is_parallel": true, "self": 89.88829578889658 }, "communicator.exchange": { "total": 1127.5410466139858, "count": 232123, "is_parallel": true, "self": 1127.5410466139858 }, "steps_from_proto": { "total": 97.3912156199579, "count": 232123, "is_parallel": true, "self": 37.053249980946646, "children": { "_process_rank_one_or_two_observation": { "total": 60.33796563901126, "count": 464246, "is_parallel": true, "self": 60.33796563901126 } } } } } } } } } } }, "trainer_advance": { "total": 505.60898807803403, "count": 232124, "self": 7.189335773075982, "children": { "process_trajectory": { "total": 164.1343395859567, "count": 232124, "self": 162.873557335957, "children": { "RLTrainer._checkpoint": { "total": 1.2607822499996928, "count": 10, "self": 1.2607822499996928 } } }, "_update_policy": { "total": 334.28531271900135, "count": 97, "self": 270.0239606930005, "children": { "TorchPPOOptimizer.update": { "total": 64.26135202600085, "count": 2910, "self": 64.26135202600085 } } } } } } }, "trainer_threads": { "total": 1.0020003173849545e-06, "count": 1, "self": 1.0020003173849545e-06 }, "TrainerController._save_models": { "total": 0.12502737800014074, "count": 1, "self": 0.0018980919999194157, "children": { "RLTrainer._checkpoint": { "total": 0.12312928600022133, "count": 1, "self": 0.12312928600022133 } } } } } } }