ppo-Pyramids / run_logs /timers.json
Adriano26's picture
First Push
41b0ed5 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.20314745604991913,
"min": 0.20036353170871735,
"max": 1.4018068313598633,
"count": 67
},
"Pyramids.Policy.Entropy.sum": {
"value": 6113.92578125,
"min": 6046.169921875,
"max": 42525.2109375,
"count": 67
},
"Pyramids.Step.mean": {
"value": 2009974.0,
"min": 29883.0,
"max": 2009974.0,
"count": 67
},
"Pyramids.Step.sum": {
"value": 2009974.0,
"min": 29883.0,
"max": 2009974.0,
"count": 67
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6510933637619019,
"min": -0.14500658214092255,
"max": 0.6842200756072998,
"count": 67
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 182.30613708496094,
"min": -34.94658660888672,
"max": 193.63427734375,
"count": 67
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.004276985768228769,
"min": -0.02534239925444126,
"max": 0.2799653708934784,
"count": 67
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 1.1975560188293457,
"min": -7.045186996459961,
"max": 67.75161743164062,
"count": 67
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06844937501133061,
"min": 0.06541937366928527,
"max": 0.07249765002953133,
"count": 67
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9582912501586285,
"min": 0.5307614199792834,
"max": 1.0678972979555565,
"count": 67
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014101383147904873,
"min": 0.00018255593427123036,
"max": 0.018534353781086838,
"count": 67
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.1974193640706682,
"min": 0.002373227145525995,
"max": 0.2594809529352157,
"count": 67
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.00010050771649745,
"min": 0.00010050771649745,
"max": 0.00029840621303126253,
"count": 67
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0014071080309643,
"min": 0.0014071080309643,
"max": 0.003801528032824033,
"count": 67
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.13350255,
"min": 0.13350255,
"max": 0.19946873750000002,
"count": 67
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.8690357,
"min": 1.5957499000000002,
"max": 2.7523842333333333,
"count": 67
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0033569047450000005,
"min": 0.0033569047450000005,
"max": 0.009946926876250001,
"count": 67
},
"Pyramids.Policy.Beta.sum": {
"value": 0.04699666643000001,
"min": 0.04699666643000001,
"max": 0.12673087907,
"count": 67
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.0056404173374176025,
"min": 0.005199231207370758,
"max": 0.3667435646057129,
"count": 67
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.07896584272384644,
"min": 0.07278923690319061,
"max": 2.933948516845703,
"count": 67
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 337.632183908046,
"min": 290.4901960784314,
"max": 999.0,
"count": 67
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29374.0,
"min": 15915.0,
"max": 32718.0,
"count": 67
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5484908863224767,
"min": -0.9998375521972775,
"max": 1.6702784138421218,
"count": 67
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 136.26719799637794,
"min": -31.99480167031288,
"max": 170.36839821189642,
"count": 67
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5484908863224767,
"min": -0.9998375521972775,
"max": 1.6702784138421218,
"count": 67
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 136.26719799637794,
"min": -31.99480167031288,
"max": 170.36839821189642,
"count": 67
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.019873120251759246,
"min": 0.016427226377841594,
"max": 7.391694875434041,
"count": 67
},
"Pyramids.Policy.RndReward.sum": {
"value": 1.7488345821548137,
"min": 1.6065027146905777,
"max": 118.26711800694466,
"count": 67
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 67
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 67
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1749148958",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1749156362"
},
"total": 7404.639835548,
"count": 1,
"self": 0.8150598689999242,
"children": {
"run_training.setup": {
"total": 0.03187451899975713,
"count": 1,
"self": 0.03187451899975713
},
"TrainerController.start_learning": {
"total": 7403.79290116,
"count": 1,
"self": 5.332359532886585,
"children": {
"TrainerController._reset_env": {
"total": 2.972464338000009,
"count": 1,
"self": 2.972464338000009
},
"TrainerController.advance": {
"total": 7395.355251487114,
"count": 129924,
"self": 5.793066790091871,
"children": {
"env_step": {
"total": 4964.024566039887,
"count": 129924,
"self": 4599.533635196667,
"children": {
"SubprocessEnvManager._take_step": {
"total": 361.4889427231037,
"count": 129924,
"self": 16.866114986912635,
"children": {
"TorchPolicy.evaluate": {
"total": 344.6228277361911,
"count": 126738,
"self": 344.6228277361911
}
}
},
"workers": {
"total": 3.0019881201160388,
"count": 129923,
"self": 0.0,
"children": {
"worker_root": {
"total": 7386.281457720919,
"count": 129923,
"is_parallel": true,
"self": 3177.5012284157865,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0030046709998714505,
"count": 1,
"is_parallel": true,
"self": 0.0010919669994109427,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019127040004605078,
"count": 8,
"is_parallel": true,
"self": 0.0019127040004605078
}
}
},
"UnityEnvironment.step": {
"total": 0.06582260300001508,
"count": 1,
"is_parallel": true,
"self": 0.0007003099995017692,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005332650002856099,
"count": 1,
"is_parallel": true,
"self": 0.0005332650002856099
},
"communicator.exchange": {
"total": 0.06259613800011721,
"count": 1,
"is_parallel": true,
"self": 0.06259613800011721
},
"steps_from_proto": {
"total": 0.001992890000110492,
"count": 1,
"is_parallel": true,
"self": 0.0004085670007043518,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015843229994061403,
"count": 8,
"is_parallel": true,
"self": 0.0015843229994061403
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 4208.780229305133,
"count": 129922,
"is_parallel": true,
"self": 98.96128254718406,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 64.61660218688439,
"count": 129922,
"is_parallel": true,
"self": 64.61660218688439
},
"communicator.exchange": {
"total": 3772.3903442479054,
"count": 129922,
"is_parallel": true,
"self": 3772.3903442479054
},
"steps_from_proto": {
"total": 272.8120003231588,
"count": 129922,
"is_parallel": true,
"self": 59.76042003351495,
"children": {
"_process_rank_one_or_two_observation": {
"total": 213.05158028964388,
"count": 1039376,
"is_parallel": true,
"self": 213.05158028964388
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 2425.537618657135,
"count": 129923,
"self": 10.179566866062942,
"children": {
"process_trajectory": {
"total": 374.1836879440898,
"count": 129923,
"self": 373.49525974109065,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6884282029991482,
"count": 4,
"self": 0.6884282029991482
}
}
},
"_update_policy": {
"total": 2041.1743638469825,
"count": 936,
"self": 799.9037303269884,
"children": {
"TorchPPOOptimizer.update": {
"total": 1241.2706335199941,
"count": 46173,
"self": 1241.2706335199941
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.9119997887173668e-06,
"count": 1,
"self": 1.9119997887173668e-06
},
"TrainerController._save_models": {
"total": 0.13282388999869,
"count": 1,
"self": 0.002962276998005109,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12986161300068488,
"count": 1,
"self": 0.12986161300068488
}
}
}
}
}
}
}