ppo-Huggy / run_logs /timers.json
vicbentu's picture
Huggy
bc3d8b7 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4066396951675415,
"min": 1.4066396951675415,
"max": 1.4275556802749634,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71002.953125,
"min": 68375.1953125,
"max": 77477.484375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 87.10796460176991,
"min": 77.21439749608764,
"max": 397.5952380952381,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49216.0,
"min": 49106.0,
"max": 50097.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999978.0,
"min": 49662.0,
"max": 1999978.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999978.0,
"min": 49662.0,
"max": 1999978.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.500054359436035,
"min": 0.20037835836410522,
"max": 2.5303001403808594,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1412.53076171875,
"min": 25.04729461669922,
"max": 1566.255859375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.87743893144405,
"min": 1.927936957359314,
"max": 4.054589884234713,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2190.752996265888,
"min": 240.99211966991425,
"max": 2497.6273686885834,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.87743893144405,
"min": 1.927936957359314,
"max": 4.054589884234713,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2190.752996265888,
"min": 240.99211966991425,
"max": 2497.6273686885834,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016136790540379784,
"min": 0.013627557707756447,
"max": 0.019201732227682237,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04841037162113935,
"min": 0.027255115415512895,
"max": 0.057605196683046714,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.051062877890136506,
"min": 0.022333445710440478,
"max": 0.062437737236420314,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15318863367040952,
"min": 0.044666891420880955,
"max": 0.18731321170926094,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6026987991333452e-06,
"min": 3.6026987991333452e-06,
"max": 0.00029534145155285,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0808096397400035e-05,
"min": 1.0808096397400035e-05,
"max": 0.0008441352186215998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10120086666666668,
"min": 0.10120086666666668,
"max": 0.19844714999999996,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30360260000000006,
"min": 0.20756169999999996,
"max": 0.5813784,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.992324666666684e-05,
"min": 6.992324666666684e-05,
"max": 0.004922512785,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020976974000000054,
"min": 0.00020976974000000054,
"max": 0.014070782159999998,
"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": "1737814458",
"python_version": "3.10.12 (main, Jan 17 2025, 14:35:34) [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+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1737816971"
},
"total": 2513.030974416,
"count": 1,
"self": 0.43724883599998066,
"children": {
"run_training.setup": {
"total": 0.023219022999967365,
"count": 1,
"self": 0.023219022999967365
},
"TrainerController.start_learning": {
"total": 2512.570506557,
"count": 1,
"self": 4.732767701880675,
"children": {
"TrainerController._reset_env": {
"total": 2.62558661099996,
"count": 1,
"self": 2.62558661099996
},
"TrainerController.advance": {
"total": 2505.0895416331196,
"count": 232949,
"self": 4.783203561107712,
"children": {
"env_step": {
"total": 1989.6702026259718,
"count": 232949,
"self": 1563.4783542529785,
"children": {
"SubprocessEnvManager._take_step": {
"total": 423.30053951198,
"count": 232949,
"self": 16.309101218023443,
"children": {
"TorchPolicy.evaluate": {
"total": 406.99143829395655,
"count": 223048,
"self": 406.99143829395655
}
}
},
"workers": {
"total": 2.891308861013158,
"count": 232949,
"self": 0.0,
"children": {
"worker_root": {
"total": 2504.9142383470435,
"count": 232949,
"is_parallel": true,
"self": 1232.479502397996,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001053132999970785,
"count": 1,
"is_parallel": true,
"self": 0.00037216599997691446,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006809669999938706,
"count": 2,
"is_parallel": true,
"self": 0.0006809669999938706
}
}
},
"UnityEnvironment.step": {
"total": 0.02943203199998834,
"count": 1,
"is_parallel": true,
"self": 0.0003215650000356618,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00018771300000253177,
"count": 1,
"is_parallel": true,
"self": 0.00018771300000253177
},
"communicator.exchange": {
"total": 0.028203634999954375,
"count": 1,
"is_parallel": true,
"self": 0.028203634999954375
},
"steps_from_proto": {
"total": 0.0007191189999957714,
"count": 1,
"is_parallel": true,
"self": 0.0002387179999914224,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00048040100000434904,
"count": 2,
"is_parallel": true,
"self": 0.00048040100000434904
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1272.4347359490475,
"count": 232948,
"is_parallel": true,
"self": 38.54363084803572,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.20452676890409,
"count": 232948,
"is_parallel": true,
"self": 84.20452676890409
},
"communicator.exchange": {
"total": 1058.1722222801034,
"count": 232948,
"is_parallel": true,
"self": 1058.1722222801034
},
"steps_from_proto": {
"total": 91.51435605200442,
"count": 232948,
"is_parallel": true,
"self": 34.087959075066976,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.42639697693744,
"count": 465896,
"is_parallel": true,
"self": 57.42639697693744
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 510.63613544604004,
"count": 232949,
"self": 7.016582781086356,
"children": {
"process_trajectory": {
"total": 172.4131961659545,
"count": 232949,
"self": 171.0851741609543,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3280220050002072,
"count": 10,
"self": 1.3280220050002072
}
}
},
"_update_policy": {
"total": 331.2063564989992,
"count": 97,
"self": 265.29745613300304,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.90890036599615,
"count": 2910,
"self": 65.90890036599615
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0159997145819943e-06,
"count": 1,
"self": 1.0159997145819943e-06
},
"TrainerController._save_models": {
"total": 0.12260959500008539,
"count": 1,
"self": 0.002010848999816517,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12059874600026887,
"count": 1,
"self": 0.12059874600026887
}
}
}
}
}
}
}