{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4065691232681274, "min": 1.4065616130828857, "max": 1.4266380071640015, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70687.1328125, "min": 68724.078125, "max": 76001.1640625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 80.68954248366013, "min": 74.05714285714286, "max": 396.92063492063494, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49382.0, "min": 48860.0, "max": 50012.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999965.0, "min": 49788.0, "max": 1999965.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999965.0, "min": 49788.0, "max": 1999965.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.5020625591278076, "min": 0.12484095245599747, "max": 2.51334285736084, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1531.2623291015625, "min": 15.605118751525879, "max": 1656.036865234375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8940602475716397, "min": 1.782347537457943, "max": 4.039578089966038, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2383.1648715138435, "min": 222.79344218224287, "max": 2604.9646540284157, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8940602475716397, "min": 1.782347537457943, "max": 4.039578089966038, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2383.1648715138435, "min": 222.79344218224287, "max": 2604.9646540284157, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016720960776304614, "min": 0.012941153750095205, "max": 0.024062282879215975, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05016288232891384, "min": 0.02588230750019041, "max": 0.05854793835799985, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.0596965428441763, "min": 0.021303860874225696, "max": 0.05980224634210268, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17908962853252888, "min": 0.04260772174845139, "max": 0.17940673902630805, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.739448753549998e-06, "min": 3.739448753549998e-06, "max": 0.000295386826537725, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1218346260649993e-05, "min": 1.1218346260649993e-05, "max": 0.0008442883685705501, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10124644999999997, "min": 0.10124644999999997, "max": 0.19846227499999997, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3037393499999999, "min": 0.2076227, "max": 0.58142945, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.219785499999996e-05, "min": 7.219785499999996e-05, "max": 0.004923267522499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021659356499999986, "min": 0.00021659356499999986, "max": 0.014073329555000003, "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": "1732501224", "python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.5.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1732503976" }, "total": 2752.7179893760003, "count": 1, "self": 0.5458745890005048, "children": { "run_training.setup": { "total": 0.1068430929999522, "count": 1, "self": 0.1068430929999522 }, "TrainerController.start_learning": { "total": 2752.065271694, "count": 1, "self": 5.210920298998644, "children": { "TrainerController._reset_env": { "total": 5.764309169000057, "count": 1, "self": 5.764309169000057 }, "TrainerController.advance": { "total": 2740.965417542001, "count": 233290, "self": 5.205355059940757, "children": { "env_step": { "total": 2186.4192607651185, "count": 233290, "self": 1717.613966493073, "children": { "SubprocessEnvManager._take_step": { "total": 465.5117008321603, "count": 233290, "self": 17.362136479295827, "children": { "TorchPolicy.evaluate": { "total": 448.14956435286445, "count": 223031, "self": 448.14956435286445 } } }, "workers": { "total": 3.293593439885285, "count": 233290, "self": 0.0, "children": { "worker_root": { "total": 2744.018938077931, "count": 233290, "is_parallel": true, "self": 1350.5122585939826, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009247760000334893, "count": 1, "is_parallel": true, "self": 0.00027967699998043827, "children": { "_process_rank_one_or_two_observation": { "total": 0.000645099000053051, "count": 2, "is_parallel": true, "self": 0.000645099000053051 } } }, "UnityEnvironment.step": { "total": 0.030983000999981414, "count": 1, "is_parallel": true, "self": 0.00038714300001174706, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002714940000032584, "count": 1, "is_parallel": true, "self": 0.0002714940000032584 }, "communicator.exchange": { "total": 0.0295964859999458, "count": 1, "is_parallel": true, "self": 0.0295964859999458 }, "steps_from_proto": { "total": 0.0007278780000206098, "count": 1, "is_parallel": true, "self": 0.00018157300007715094, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005463049999434588, "count": 2, "is_parallel": true, "self": 0.0005463049999434588 } } } } } } }, "UnityEnvironment.step": { "total": 1393.5066794839486, "count": 233289, "is_parallel": true, "self": 41.23290916307542, "children": { "UnityEnvironment._generate_step_input": { "total": 93.76746445693948, "count": 233289, "is_parallel": true, "self": 93.76746445693948 }, "communicator.exchange": { "total": 1159.0937878449743, "count": 233289, "is_parallel": true, "self": 1159.0937878449743 }, "steps_from_proto": { "total": 99.41251801895953, "count": 233289, "is_parallel": true, "self": 37.64519304392911, "children": { "_process_rank_one_or_two_observation": { "total": 61.76732497503042, "count": 466578, "is_parallel": true, "self": 61.76732497503042 } } } } } } } } } } }, "trainer_advance": { "total": 549.3408017169419, "count": 233290, "self": 7.285837245932953, "children": { "process_trajectory": { "total": 198.59028104600884, "count": 233290, "self": 197.17371358500907, "children": { "RLTrainer._checkpoint": { "total": 1.4165674609997723, "count": 10, "self": 1.4165674609997723 } } }, "_update_policy": { "total": 343.4646834250001, "count": 97, "self": 275.715297020005, "children": { "TorchPPOOptimizer.update": { "total": 67.74938640499511, "count": 2910, "self": 67.74938640499511 } } } } } } }, "trainer_threads": { "total": 1.1170000107085798e-06, "count": 1, "self": 1.1170000107085798e-06 }, "TrainerController._save_models": { "total": 0.12462356700007149, "count": 1, "self": 0.0023049770002216974, "children": { "RLTrainer._checkpoint": { "total": 0.12231858999984979, "count": 1, "self": 0.12231858999984979 } } } } } } }