ppo-Pyramids / run_logs /timers.json
B-ramB's picture
first push
80b223e verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5750015377998352,
"min": 0.5750015377998352,
"max": 1.4115815162658691,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 17176.4453125,
"min": 17176.4453125,
"max": 42821.73828125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989913.0,
"min": 29952.0,
"max": 989913.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989913.0,
"min": 29952.0,
"max": 989913.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.36547932028770447,
"min": -0.07051515579223633,
"max": 0.40822452306747437,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 97.58297729492188,
"min": -17.135183334350586,
"max": 110.62884521484375,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.021197589114308357,
"min": -0.021197589114308357,
"max": 0.3482414186000824,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -5.659756183624268,
"min": -5.659756183624268,
"max": 82.53321838378906,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06999735412925172,
"min": 0.06388624965426323,
"max": 0.07398575549074127,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9799629578095241,
"min": 0.5179002884351889,
"max": 1.0487339820578128,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.012556396631268963,
"min": 0.0012354213615323462,
"max": 0.013578061783078332,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.17578955283776548,
"min": 0.016061872325673025,
"max": 0.20367092674617499,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.557504623721428e-06,
"min": 7.557504623721428e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010580506473209999,
"min": 0.00010580506473209999,
"max": 0.0035082479305840993,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10251913571428574,
"min": 0.10251913571428574,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4352679000000004,
"min": 1.3886848,
"max": 2.5694159,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026166165785714284,
"min": 0.00026166165785714284,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036632632099999995,
"min": 0.0036632632099999995,
"max": 0.11696464840999998,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01079276017844677,
"min": 0.01079276017844677,
"max": 0.3692036271095276,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.15109863877296448,
"min": 0.15109863877296448,
"max": 2.584425449371338,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 464.5,
"min": 438.4852941176471,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 32515.0,
"min": 15984.0,
"max": 33542.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.278282831715686,
"min": -1.0000000521540642,
"max": 1.384994096287033,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 89.47979822009802,
"min": -30.570001661777496,
"max": 94.17959854751825,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.278282831715686,
"min": -1.0000000521540642,
"max": 1.384994096287033,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 89.47979822009802,
"min": -30.570001661777496,
"max": 94.17959854751825,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.05271106137287071,
"min": 0.05271106137287071,
"max": 6.776054756715894,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.68977429610095,
"min": 3.451392070914153,
"max": 108.4168761074543,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1747483001",
"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/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1747485227"
},
"total": 2226.25932422,
"count": 1,
"self": 0.4763454119997732,
"children": {
"run_training.setup": {
"total": 0.019730811000044923,
"count": 1,
"self": 0.019730811000044923
},
"TrainerController.start_learning": {
"total": 2225.7632479970002,
"count": 1,
"self": 1.3838735289323267,
"children": {
"TrainerController._reset_env": {
"total": 2.232489079000061,
"count": 1,
"self": 2.232489079000061
},
"TrainerController.advance": {
"total": 2222.0644522090674,
"count": 63481,
"self": 1.3811116760971345,
"children": {
"env_step": {
"total": 1558.2634805320213,
"count": 63481,
"self": 1410.902289320074,
"children": {
"SubprocessEnvManager._take_step": {
"total": 146.60519658998783,
"count": 63481,
"self": 4.523621947042557,
"children": {
"TorchPolicy.evaluate": {
"total": 142.08157464294527,
"count": 62546,
"self": 142.08157464294527
}
}
},
"workers": {
"total": 0.7559946219594167,
"count": 63481,
"self": 0.0,
"children": {
"worker_root": {
"total": 2220.804901567104,
"count": 63481,
"is_parallel": true,
"self": 919.5645264082045,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020163359999969543,
"count": 1,
"is_parallel": true,
"self": 0.0006702330001644441,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013461029998325102,
"count": 8,
"is_parallel": true,
"self": 0.0013461029998325102
}
}
},
"UnityEnvironment.step": {
"total": 0.047777899999800866,
"count": 1,
"is_parallel": true,
"self": 0.0005583439992733474,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004460540003492497,
"count": 1,
"is_parallel": true,
"self": 0.0004460540003492497
},
"communicator.exchange": {
"total": 0.04506952900010219,
"count": 1,
"is_parallel": true,
"self": 0.04506952900010219
},
"steps_from_proto": {
"total": 0.0017039730000760756,
"count": 1,
"is_parallel": true,
"self": 0.0003666389998215891,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013373340002544865,
"count": 8,
"is_parallel": true,
"self": 0.0013373340002544865
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1301.2403751588995,
"count": 63480,
"is_parallel": true,
"self": 31.245123595055247,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.93360255797188,
"count": 63480,
"is_parallel": true,
"self": 22.93360255797188
},
"communicator.exchange": {
"total": 1151.9770538009939,
"count": 63480,
"is_parallel": true,
"self": 1151.9770538009939
},
"steps_from_proto": {
"total": 95.0845952048785,
"count": 63480,
"is_parallel": true,
"self": 19.058988806874368,
"children": {
"_process_rank_one_or_two_observation": {
"total": 76.02560639800413,
"count": 507840,
"is_parallel": true,
"self": 76.02560639800413
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 662.419860000949,
"count": 63481,
"self": 2.6104520580461212,
"children": {
"process_trajectory": {
"total": 127.3526547029046,
"count": 63481,
"self": 127.15831363090456,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1943410720000429,
"count": 2,
"self": 0.1943410720000429
}
}
},
"_update_policy": {
"total": 532.4567532399983,
"count": 450,
"self": 298.3372291050291,
"children": {
"TorchPPOOptimizer.update": {
"total": 234.1195241349692,
"count": 22782,
"self": 234.1195241349692
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0009998732130043e-06,
"count": 1,
"self": 1.0009998732130043e-06
},
"TrainerController._save_models": {
"total": 0.08243217900053423,
"count": 1,
"self": 0.001145611000538338,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0812865679999959,
"count": 1,
"self": 0.0812865679999959
}
}
}
}
}
}
}