{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4055145978927612, "min": 1.4055145978927612, "max": 1.4269826412200928, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 67835.7578125, "min": 67835.7578125, "max": 79161.4609375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 98.01383399209486, "min": 79.2711038961039, "max": 387.4031007751938, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49595.0, "min": 48821.0, "max": 50176.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999954.0, "min": 49799.0, "max": 1999954.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999954.0, "min": 49799.0, "max": 1999954.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.454477310180664, "min": 0.15040063858032227, "max": 2.483915090560913, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1239.510986328125, "min": 19.25128173828125, "max": 1507.503173828125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8275354002962017, "min": 1.8283972421195358, "max": 3.947026188202946, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1932.905377149582, "min": 234.03484699130058, "max": 2352.475210428238, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8275354002962017, "min": 1.8283972421195358, "max": 3.947026188202946, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1932.905377149582, "min": 234.03484699130058, "max": 2352.475210428238, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.014754568874033995, "min": 0.013805214732565218, "max": 0.02116363122780361, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04426370662210199, "min": 0.027610429465130436, "max": 0.056416178705209555, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.051119404617283086, "min": 0.022349881722281376, "max": 0.06393321920186282, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15335821385184925, "min": 0.04469976344456275, "max": 0.18221742138266564, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.5303988232333315e-06, "min": 3.5303988232333315e-06, "max": 0.00029535652654782496, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0591196469699995e-05, "min": 1.0591196469699995e-05, "max": 0.0008442583685805499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10117676666666664, "min": 0.10117676666666664, "max": 0.19845217499999998, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3035302999999999, "min": 0.20755310000000005, "max": 0.5814194499999998, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.872065666666662e-05, "min": 6.872065666666662e-05, "max": 0.0049227635325, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020616196999999987, "min": 0.00020616196999999987, "max": 0.014072830554999999, "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": "1737151580", "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]", "command_line_arguments": "/home/leo/anaconda3/envs/hf_rl/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+cu124", "numpy_version": "1.23.5", "end_time_seconds": "1737152584" }, "total": 1003.890863631852, "count": 1, "self": 0.1668196776881814, "children": { "run_training.setup": { "total": 0.008168132975697517, "count": 1, "self": 0.008168132975697517 }, "TrainerController.start_learning": { "total": 1003.7158758211881, "count": 1, "self": 2.4578376412391663, "children": { "TrainerController._reset_env": { "total": 0.8373665101826191, "count": 1, "self": 0.8373665101826191 }, "TrainerController.advance": { "total": 1000.3705596008804, "count": 232710, "self": 2.076642765197903, "children": { "env_step": { "total": 780.9508170231711, "count": 232710, "self": 545.2146916696802, "children": { "SubprocessEnvManager._take_step": { "total": 234.17086226004176, "count": 232710, "self": 7.6863045047502965, "children": { "TorchPolicy.evaluate": { "total": 226.48455775529146, "count": 222926, "self": 226.48455775529146 } } }, "workers": { "total": 1.5652630934491754, "count": 232710, "self": 0.0, "children": { "worker_root": { "total": 1001.0627308150288, "count": 232710, "is_parallel": true, "self": 577.6231672195718, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0003269738517701626, "count": 1, "is_parallel": true, "self": 8.336990140378475e-05, "children": { "_process_rank_one_or_two_observation": { "total": 0.00024360395036637783, "count": 2, "is_parallel": true, "self": 0.00024360395036637783 } } }, "UnityEnvironment.step": { "total": 0.009991917992010713, "count": 1, "is_parallel": true, "self": 0.00010750512592494488, "children": { "UnityEnvironment._generate_step_input": { "total": 9.197392500936985e-05, "count": 1, "is_parallel": true, "self": 9.197392500936985e-05 }, "communicator.exchange": { "total": 0.009573000017553568, "count": 1, "is_parallel": true, "self": 0.009573000017553568 }, "steps_from_proto": { "total": 0.00021943892352283, "count": 1, "is_parallel": true, "self": 6.031780503690243e-05, "children": { "_process_rank_one_or_two_observation": { "total": 0.00015912111848592758, "count": 2, "is_parallel": true, "self": 0.00015912111848592758 } } } } } } }, "UnityEnvironment.step": { "total": 423.439563595457, "count": 232709, "is_parallel": true, "self": 12.39814013778232, "children": { "UnityEnvironment._generate_step_input": { "total": 21.172899830620736, "count": 232709, "is_parallel": true, "self": 21.172899830620736 }, "communicator.exchange": { "total": 362.4556123474613, "count": 232709, "is_parallel": true, "self": 362.4556123474613 }, "steps_from_proto": { "total": 27.412911279592663, "count": 232709, "is_parallel": true, "self": 8.995051546953619, "children": { "_process_rank_one_or_two_observation": { "total": 18.417859732639045, "count": 465418, "is_parallel": true, "self": 18.417859732639045 } } } } } } } } } } }, "trainer_advance": { "total": 217.34309981251135, "count": 232710, "self": 3.5894014181103557, "children": { "process_trajectory": { "total": 87.16914816340432, "count": 232710, "self": 86.4229914394673, "children": { "RLTrainer._checkpoint": { "total": 0.7461567239370197, "count": 10, "self": 0.7461567239370197 } } }, "_update_policy": { "total": 126.58455023099668, "count": 97, "self": 97.9210453343112, "children": { "TorchPPOOptimizer.update": { "total": 28.66350489668548, "count": 2910, "self": 28.66350489668548 } } } } } } }, "trainer_threads": { "total": 6.419140845537186e-07, "count": 1, "self": 6.419140845537186e-07 }, "TrainerController._save_models": { "total": 0.05011142697185278, "count": 1, "self": 0.0008182378951460123, "children": { "RLTrainer._checkpoint": { "total": 0.04929318907670677, "count": 1, "self": 0.04929318907670677 } } } } } } }