{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4040008783340454, "min": 1.4040008783340454, "max": 1.426756739616394, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69740.9375, "min": 69122.1796875, "max": 76295.6171875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 120.70217917675545, "min": 98.63872255489022, "max": 420.4621848739496, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49850.0, "min": 49329.0, "max": 50193.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999733.0, "min": 49731.0, "max": 1999733.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999733.0, "min": 49731.0, "max": 1999733.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3494231700897217, "min": 0.06956339627504349, "max": 2.4434354305267334, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 970.311767578125, "min": 8.208480834960938, "max": 1172.4449462890625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5808509960590205, "min": 1.9839238388053442, "max": 3.923724335824658, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1478.8914613723755, "min": 234.1030129790306, "max": 1965.7858922481537, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5808509960590205, "min": 1.9839238388053442, "max": 3.923724335824658, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1478.8914613723755, "min": 234.1030129790306, "max": 1965.7858922481537, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018727165893263495, "min": 0.013916071372417113, "max": 0.020090323896632373, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03745433178652699, "min": 0.027832142744834226, "max": 0.056820248164634296, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04042751099914312, "min": 0.02243384045238296, "max": 0.05515643937720193, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.08085502199828624, "min": 0.04486768090476592, "max": 0.16546931813160579, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.3758235414250024e-06, "min": 4.3758235414250024e-06, "max": 0.00029529727656757497, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.751647082850005e-06, "min": 8.751647082850005e-06, "max": 0.0008439946686684499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10145857500000002, "min": 0.10145857500000002, "max": 0.19843242500000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20291715000000005, "min": 0.20291715000000005, "max": 0.58133155, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.278289250000003e-05, "min": 8.278289250000003e-05, "max": 0.0049217780075000005, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00016556578500000007, "min": 0.00016556578500000007, "max": 0.014068444344999998, "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": "1695181655", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1695184198" }, "total": 2542.3881051430003, "count": 1, "self": 0.43790090400034387, "children": { "run_training.setup": { "total": 0.04239853999990828, "count": 1, "self": 0.04239853999990828 }, "TrainerController.start_learning": { "total": 2541.907805699, "count": 1, "self": 4.708324431986057, "children": { "TrainerController._reset_env": { "total": 4.061715916000026, "count": 1, "self": 4.061715916000026 }, "TrainerController.advance": { "total": 2533.015918089014, "count": 231047, "self": 4.800607487965408, "children": { "env_step": { "total": 1978.4069043950942, "count": 231047, "self": 1665.1260210491598, "children": { "SubprocessEnvManager._take_step": { "total": 310.18578700900036, "count": 231047, "self": 18.01075285803904, "children": { "TorchPolicy.evaluate": { "total": 292.1750341509613, "count": 222983, "self": 292.1750341509613 } } }, "workers": { "total": 3.0950963369340343, "count": 231047, "self": 0.0, "children": { "worker_root": { "total": 2534.110241940989, "count": 231047, "is_parallel": true, "self": 1181.1900257880877, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009145860000216999, "count": 1, "is_parallel": true, "self": 0.00028032100010477734, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006342649999169225, "count": 2, "is_parallel": true, "self": 0.0006342649999169225 } } }, "UnityEnvironment.step": { "total": 0.02907823099997131, "count": 1, "is_parallel": true, "self": 0.00034277699990070687, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00024481100001594314, "count": 1, "is_parallel": true, "self": 0.00024481100001594314 }, "communicator.exchange": { "total": 0.02774983799997699, "count": 1, "is_parallel": true, "self": 0.02774983799997699 }, "steps_from_proto": { "total": 0.0007408050000776711, "count": 1, "is_parallel": true, "self": 0.00019951400008721976, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005412909999904514, "count": 2, "is_parallel": true, "self": 0.0005412909999904514 } } } } } } }, "UnityEnvironment.step": { "total": 1352.9202161529013, "count": 231046, "is_parallel": true, "self": 40.48047007365244, "children": { "UnityEnvironment._generate_step_input": { "total": 86.23589757305956, "count": 231046, "is_parallel": true, "self": 86.23589757305956 }, "communicator.exchange": { "total": 1124.27959655911, "count": 231046, "is_parallel": true, "self": 1124.27959655911 }, "steps_from_proto": { "total": 101.9242519470796, "count": 231046, "is_parallel": true, "self": 38.43110936205255, "children": { "_process_rank_one_or_two_observation": { "total": 63.493142585027044, "count": 462092, "is_parallel": true, "self": 63.493142585027044 } } } } } } } } } } }, "trainer_advance": { "total": 549.8084062059545, "count": 231047, "self": 6.961343301906595, "children": { "process_trajectory": { "total": 140.62062522104782, "count": 231047, "self": 139.3285909100473, "children": { "RLTrainer._checkpoint": { "total": 1.2920343110005206, "count": 10, "self": 1.2920343110005206 } } }, "_update_policy": { "total": 402.2264376830001, "count": 96, "self": 341.6507320600065, "children": { "TorchPPOOptimizer.update": { "total": 60.57570562299361, "count": 2880, "self": 60.57570562299361 } } } } } } }, "trainer_threads": { "total": 9.919999683916103e-07, "count": 1, "self": 9.919999683916103e-07 }, "TrainerController._save_models": { "total": 0.12184626999987813, "count": 1, "self": 0.0020207889997436723, "children": { "RLTrainer._checkpoint": { "total": 0.11982548100013446, "count": 1, "self": 0.11982548100013446 } } } } } } }