{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4022271633148193, "min": 1.4022271633148193, "max": 1.4228541851043701, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 67984.1796875, "min": 67663.15625, "max": 76558.0234375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 94.3011583011583, "min": 88.8850987432675, "max": 400.28, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48848.0, "min": 48848.0, "max": 50224.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999979.0, "min": 49872.0, "max": 1999979.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999979.0, "min": 49872.0, "max": 1999979.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.37518572807312, "min": 0.03540293127298355, "max": 2.4542548656463623, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1230.34619140625, "min": 4.389963626861572, "max": 1367.02001953125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.6448284727035802, "min": 1.7572824023663998, "max": 3.8702333417945893, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1888.0211488604546, "min": 217.90301789343357, "max": 2111.0700077414513, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.6448284727035802, "min": 1.7572824023663998, "max": 3.8702333417945893, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1888.0211488604546, "min": 217.90301789343357, "max": 2111.0700077414513, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01589588800658627, "min": 0.013220963542537196, "max": 0.019968166531665096, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04768766401975881, "min": 0.02827900303915764, "max": 0.05905510728480294, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05533361890249782, "min": 0.02337155183777213, "max": 0.05965041071176529, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16600085670749345, "min": 0.04674310367554426, "max": 0.17509808378914993, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.3255488915166628e-06, "min": 3.3255488915166628e-06, "max": 0.0002953575015474999, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.976646674549988e-06, "min": 9.976646674549988e-06, "max": 0.0008441985186004998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10110848333333333, "min": 0.10110848333333333, "max": 0.19845249999999995, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30332545, "min": 0.20740560000000002, "max": 0.5813995, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.531331833333329e-05, "min": 6.531331833333329e-05, "max": 0.004922779750000002, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00019593995499999985, "min": 0.00019593995499999985, "max": 0.014071835049999998, "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": "1717645558", "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": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1717647916" }, "total": 2357.949461827, "count": 1, "self": 0.4377835150003193, "children": { "run_training.setup": { "total": 0.05761760700005425, "count": 1, "self": 0.05761760700005425 }, "TrainerController.start_learning": { "total": 2357.454060705, "count": 1, "self": 4.241282291052812, "children": { "TrainerController._reset_env": { "total": 3.8132384269999875, "count": 1, "self": 3.8132384269999875 }, "TrainerController.advance": { "total": 2349.2899016599467, "count": 231826, "self": 4.503006303873008, "children": { "env_step": { "total": 1861.7516610639943, "count": 231826, "self": 1531.2602368249568, "children": { "SubprocessEnvManager._take_step": { "total": 327.7136535330231, "count": 231826, "self": 16.778999077041874, "children": { "TorchPolicy.evaluate": { "total": 310.9346544559812, "count": 222936, "self": 310.9346544559812 } } }, "workers": { "total": 2.777770706014394, "count": 231826, "self": 0.0, "children": { "worker_root": { "total": 2350.6775602479315, "count": 231826, "is_parallel": true, "self": 1118.591792168974, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008715600000073209, "count": 1, "is_parallel": true, "self": 0.00021398600000566148, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006575740000016594, "count": 2, "is_parallel": true, "self": 0.0006575740000016594 } } }, "UnityEnvironment.step": { "total": 0.0289302090000092, "count": 1, "is_parallel": true, "self": 0.0003824020000138262, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020972600003688058, "count": 1, "is_parallel": true, "self": 0.00020972600003688058 }, "communicator.exchange": { "total": 0.0275881439999921, "count": 1, "is_parallel": true, "self": 0.0275881439999921 }, "steps_from_proto": { "total": 0.0007499369999663941, "count": 1, "is_parallel": true, "self": 0.00021387499992897574, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005360620000374183, "count": 2, "is_parallel": true, "self": 0.0005360620000374183 } } } } } } }, "UnityEnvironment.step": { "total": 1232.0857680789575, "count": 231825, "is_parallel": true, "self": 38.32612634899397, "children": { "UnityEnvironment._generate_step_input": { "total": 79.42187222303312, "count": 231825, "is_parallel": true, "self": 79.42187222303312 }, "communicator.exchange": { "total": 1026.7443754359408, "count": 231825, "is_parallel": true, "self": 1026.7443754359408 }, "steps_from_proto": { "total": 87.59339407098952, "count": 231825, "is_parallel": true, "self": 31.0229984689978, "children": { "_process_rank_one_or_two_observation": { "total": 56.57039560199172, "count": 463650, "is_parallel": true, "self": 56.57039560199172 } } } } } } } } } } }, "trainer_advance": { "total": 483.03523429207945, "count": 231826, "self": 6.449697808148301, "children": { "process_trajectory": { "total": 150.51292582892887, "count": 231826, "self": 149.2003142779294, "children": { "RLTrainer._checkpoint": { "total": 1.3126115509994634, "count": 10, "self": 1.3126115509994634 } } }, "_update_policy": { "total": 326.0726106550023, "count": 97, "self": 261.8221759529989, "children": { "TorchPPOOptimizer.update": { "total": 64.25043470200336, "count": 2910, "self": 64.25043470200336 } } } } } } }, "trainer_threads": { "total": 9.7599968285067e-07, "count": 1, "self": 9.7599968285067e-07 }, "TrainerController._save_models": { "total": 0.1096373510004014, "count": 1, "self": 0.002528805000565626, "children": { "RLTrainer._checkpoint": { "total": 0.10710854599983577, "count": 1, "self": 0.10710854599983577 } } } } } } }