ppo-Huggy / run_logs /timers.json
junqin's picture
Huggy
c3bde69 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4124925136566162,
"min": 1.4124925136566162,
"max": 1.4334990978240967,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69542.65625,
"min": 69165.4296875,
"max": 77893.734375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 84.79725085910653,
"min": 81.35090609555189,
"max": 398.468253968254,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49352.0,
"min": 48840.0,
"max": 50207.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999928.0,
"min": 49919.0,
"max": 1999928.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999928.0,
"min": 49919.0,
"max": 1999928.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4851841926574707,
"min": -0.012192162685096264,
"max": 2.5103957653045654,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1446.377197265625,
"min": -1.5240203142166138,
"max": 1489.73046875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9299762780518877,
"min": 1.8875021364688873,
"max": 3.939956378998748,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2287.2461938261986,
"min": 235.93776705861092,
"max": 2305.244613945484,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9299762780518877,
"min": 1.8875021364688873,
"max": 3.939956378998748,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2287.2461938261986,
"min": 235.93776705861092,
"max": 2305.244613945484,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.0161593208678015,
"min": 0.012570540346011209,
"max": 0.02016510261649576,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04847796260340449,
"min": 0.025141080692022418,
"max": 0.059300907036231365,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.057868998580508764,
"min": 0.020538768855233987,
"max": 0.0681622774236732,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1736069957415263,
"min": 0.04107753771046797,
"max": 0.2044868322710196,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7268987577333297e-06,
"min": 3.7268987577333297e-06,
"max": 0.00029535877654707503,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.118069627319999e-05,
"min": 1.118069627319999e-05,
"max": 0.00084414736861755,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10124226666666665,
"min": 0.10124226666666665,
"max": 0.19845292499999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30372679999999996,
"min": 0.20761675000000004,
"max": 0.5813824500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.198910666666659e-05,
"min": 7.198910666666659e-05,
"max": 0.004922800957499998,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002159673199999998,
"min": 0.0002159673199999998,
"max": 0.014070984255,
"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": "1740059998",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1740062449"
},
"total": 2450.2043724249997,
"count": 1,
"self": 0.43727395199994135,
"children": {
"run_training.setup": {
"total": 0.03045084300003964,
"count": 1,
"self": 0.03045084300003964
},
"TrainerController.start_learning": {
"total": 2449.73664763,
"count": 1,
"self": 4.254462612933821,
"children": {
"TrainerController._reset_env": {
"total": 3.1886170669999956,
"count": 1,
"self": 3.1886170669999956
},
"TrainerController.advance": {
"total": 2442.177890685066,
"count": 231885,
"self": 4.834127355044984,
"children": {
"env_step": {
"total": 1947.39082397706,
"count": 231885,
"self": 1528.1091650619674,
"children": {
"SubprocessEnvManager._take_step": {
"total": 416.6751699830405,
"count": 231885,
"self": 15.927010052992273,
"children": {
"TorchPolicy.evaluate": {
"total": 400.74815993004825,
"count": 222871,
"self": 400.74815993004825
}
}
},
"workers": {
"total": 2.6064889320523434,
"count": 231885,
"self": 0.0,
"children": {
"worker_root": {
"total": 2442.0586368780096,
"count": 231885,
"is_parallel": true,
"self": 1193.5593854380113,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00104739799996878,
"count": 1,
"is_parallel": true,
"self": 0.00040795500001422624,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006394429999545537,
"count": 2,
"is_parallel": true,
"self": 0.0006394429999545537
}
}
},
"UnityEnvironment.step": {
"total": 0.029338349999989077,
"count": 1,
"is_parallel": true,
"self": 0.0003375049999476687,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001858250000168482,
"count": 1,
"is_parallel": true,
"self": 0.0001858250000168482
},
"communicator.exchange": {
"total": 0.028110499000035816,
"count": 1,
"is_parallel": true,
"self": 0.028110499000035816
},
"steps_from_proto": {
"total": 0.0007045209999887447,
"count": 1,
"is_parallel": true,
"self": 0.00018827799988230254,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005162430001064422,
"count": 2,
"is_parallel": true,
"self": 0.0005162430001064422
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1248.4992514399983,
"count": 231884,
"is_parallel": true,
"self": 37.5396655389095,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 82.6184589219489,
"count": 231884,
"is_parallel": true,
"self": 82.6184589219489
},
"communicator.exchange": {
"total": 1039.5613063190613,
"count": 231884,
"is_parallel": true,
"self": 1039.5613063190613
},
"steps_from_proto": {
"total": 88.77982066007883,
"count": 231884,
"is_parallel": true,
"self": 32.986717788032365,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.79310287204646,
"count": 463768,
"is_parallel": true,
"self": 55.79310287204646
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 489.9529393529606,
"count": 231885,
"self": 6.4160465349464175,
"children": {
"process_trajectory": {
"total": 159.25076273301465,
"count": 231885,
"self": 157.93199976401456,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3187629690000904,
"count": 10,
"self": 1.3187629690000904
}
}
},
"_update_policy": {
"total": 324.2861300849995,
"count": 97,
"self": 259.70171789900917,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.58441218599035,
"count": 2910,
"self": 64.58441218599035
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0170001587539446e-06,
"count": 1,
"self": 1.0170001587539446e-06
},
"TrainerController._save_models": {
"total": 0.11567624799999976,
"count": 1,
"self": 0.0018937220002044342,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11378252599979533,
"count": 1,
"self": 0.11378252599979533
}
}
}
}
}
}
}