{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4073259830474854, "min": 1.4073259830474854, "max": 1.4273267984390259, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 72245.078125, "min": 69184.1640625, "max": 76074.109375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 80.19318181818181, "min": 70.46, "max": 377.56390977443607, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49399.0, "min": 49044.0, "max": 50216.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999934.0, "min": 49733.0, "max": 1999934.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999934.0, "min": 49733.0, "max": 1999934.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.520026445388794, "min": 0.10002531856298447, "max": 2.542757749557495, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1552.3363037109375, "min": 13.20334243774414, "max": 1779.930419921875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.96726676366933, "min": 1.8684599816121839, "max": 4.113958208619615, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2443.836326420307, "min": 246.63671757280827, "max": 2731.7513710856438, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.96726676366933, "min": 1.8684599816121839, "max": 4.113958208619615, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2443.836326420307, "min": 246.63671757280827, "max": 2731.7513710856438, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018714974201025646, "min": 0.012646318567810037, "max": 0.021522284468907554, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.056144922603076935, "min": 0.025292637135620074, "max": 0.05640557738212616, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05210017433596983, "min": 0.02188228784749905, "max": 0.06209501804163059, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15630052300790948, "min": 0.0437645756949981, "max": 0.1765675405661265, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.909698696800002e-06, "min": 3.909698696800002e-06, "max": 0.0002953064265645249, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1729096090400006e-05, "min": 1.1729096090400006e-05, "max": 0.0008439342186886001, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.1013032, "min": 0.1013032, "max": 0.19843547500000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3039096, "min": 0.20774884999999998, "max": 0.5813113999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.502968000000004e-05, "min": 7.502968000000004e-05, "max": 0.004921930202499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002250890400000001, "min": 0.0002250890400000001, "max": 0.01406743886, "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": "1702992525", "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=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702995125" }, "total": 2600.150216784, "count": 1, "self": 0.5555386259998158, "children": { "run_training.setup": { "total": 0.05078170800015869, "count": 1, "self": 0.05078170800015869 }, "TrainerController.start_learning": { "total": 2599.54389645, "count": 1, "self": 4.883474503996695, "children": { "TrainerController._reset_env": { "total": 3.325823573999969, "count": 1, "self": 3.325823573999969 }, "TrainerController.advance": { "total": 2591.2163347570036, "count": 233741, "self": 5.192997166916484, "children": { "env_step": { "total": 2036.4192825591656, "count": 233741, "self": 1693.4283782652094, "children": { "SubprocessEnvManager._take_step": { "total": 339.8819713970465, "count": 233741, "self": 18.54272205007146, "children": { "TorchPolicy.evaluate": { "total": 321.33924934697507, "count": 223053, "self": 321.33924934697507 } } }, "workers": { "total": 3.108932896909664, "count": 233741, "self": 0.0, "children": { "worker_root": { "total": 2591.8339128920597, "count": 233741, "is_parallel": true, "self": 1219.0671845870731, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0006844160000127886, "count": 1, "is_parallel": true, "self": 0.00022426200007430452, "children": { "_process_rank_one_or_two_observation": { "total": 0.00046015399993848405, "count": 2, "is_parallel": true, "self": 0.00046015399993848405 } } }, "UnityEnvironment.step": { "total": 0.03522680599985506, "count": 1, "is_parallel": true, "self": 0.000328566999769464, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002169790000152716, "count": 1, "is_parallel": true, "self": 0.0002169790000152716 }, "communicator.exchange": { "total": 0.03391891000001124, "count": 1, "is_parallel": true, "self": 0.03391891000001124 }, "steps_from_proto": { "total": 0.0007623500000590866, "count": 1, "is_parallel": true, "self": 0.0002079639998555649, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005543860002035217, "count": 2, "is_parallel": true, "self": 0.0005543860002035217 } } } } } } }, "UnityEnvironment.step": { "total": 1372.7667283049866, "count": 233740, "is_parallel": true, "self": 42.60082515597924, "children": { "UnityEnvironment._generate_step_input": { "total": 89.48527045395076, "count": 233740, "is_parallel": true, "self": 89.48527045395076 }, "communicator.exchange": { "total": 1144.225593093045, "count": 233740, "is_parallel": true, "self": 1144.225593093045 }, "steps_from_proto": { "total": 96.45503960201154, "count": 233740, "is_parallel": true, "self": 35.85881824902822, "children": { "_process_rank_one_or_two_observation": { "total": 60.59622135298332, "count": 467480, "is_parallel": true, "self": 60.59622135298332 } } } } } } } } } } }, "trainer_advance": { "total": 549.6040550309215, "count": 233741, "self": 7.066664288956645, "children": { "process_trajectory": { "total": 167.9927145839638, "count": 233741, "self": 166.76905197596375, "children": { "RLTrainer._checkpoint": { "total": 1.2236626080000406, "count": 10, "self": 1.2236626080000406 } } }, "_update_policy": { "total": 374.54467615800104, "count": 97, "self": 307.74507431101097, "children": { "TorchPPOOptimizer.update": { "total": 66.79960184699007, "count": 2910, "self": 66.79960184699007 } } } } } } }, "trainer_threads": { "total": 9.929999578162096e-07, "count": 1, "self": 9.929999578162096e-07 }, "TrainerController._save_models": { "total": 0.11826262199974735, "count": 1, "self": 0.0019531179996192805, "children": { "RLTrainer._checkpoint": { "total": 0.11630950400012807, "count": 1, "self": 0.11630950400012807 } } } } } } }