ppo-PyramidsRND / run_logs /timers.json
kelvinksau's picture
First Push
520158f verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.406842976808548,
"min": 0.406842976808548,
"max": 1.453125238418579,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12250.85546875,
"min": 12054.646484375,
"max": 44082.0078125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989939.0,
"min": 29971.0,
"max": 989939.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989939.0,
"min": 29971.0,
"max": 989939.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.522752046585083,
"min": -0.10752847790718079,
"max": 0.5949802398681641,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 145.8478240966797,
"min": -26.021892547607422,
"max": 167.189453125,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.052198924124240875,
"min": -0.0018358691595494747,
"max": 0.42513546347618103,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 14.563499450683594,
"min": -0.5085357427597046,
"max": 101.18224334716797,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06685773237970555,
"min": 0.06378978480084692,
"max": 0.07216945448223468,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0028659856955833,
"min": 0.48100804635183086,
"max": 1.0621481509548245,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014325529872439801,
"min": 0.00022832893310349153,
"max": 0.016164524991056948,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21488294808659703,
"min": 0.00296827613034539,
"max": 0.22630334987479725,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.460317513259998e-06,
"min": 7.460317513259998e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011190476269889997,
"min": 0.00011190476269889997,
"max": 0.003633033188989,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10248674,
"min": 0.10248674,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5373011,
"min": 1.3886848,
"max": 2.611011,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025842532600000006,
"min": 0.00025842532600000006,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003876379890000001,
"min": 0.003876379890000001,
"max": 0.12111999890000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010371810756623745,
"min": 0.010371810756623745,
"max": 0.4345143437385559,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1555771678686142,
"min": 0.14637142419815063,
"max": 3.041600465774536,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 374.70238095238096,
"min": 339.8426966292135,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31475.0,
"min": 16770.0,
"max": 33536.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6014809353010995,
"min": -0.999871019394167,
"max": 1.6052952241152525,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 134.52439856529236,
"min": -30.996001601219177,
"max": 137.95599825680256,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6014809353010995,
"min": -0.999871019394167,
"max": 1.6052952241152525,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 134.52439856529236,
"min": -30.996001601219177,
"max": 137.95599825680256,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04032923022601781,
"min": 0.036921987365365734,
"max": 7.8954791935051185,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.387655338985496,
"min": 3.2491348881521844,
"max": 134.22314628958702,
"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": "1742187092",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1742189286"
},
"total": 2194.774524753,
"count": 1,
"self": 0.47591002599983767,
"children": {
"run_training.setup": {
"total": 0.02034394199995404,
"count": 1,
"self": 0.02034394199995404
},
"TrainerController.start_learning": {
"total": 2194.278270785,
"count": 1,
"self": 1.6600702439582165,
"children": {
"TrainerController._reset_env": {
"total": 2.134385484999939,
"count": 1,
"self": 2.134385484999939
},
"TrainerController.advance": {
"total": 2190.3986174200422,
"count": 63704,
"self": 1.6357299000451349,
"children": {
"env_step": {
"total": 1509.7856307700504,
"count": 63704,
"self": 1341.1788968562084,
"children": {
"SubprocessEnvManager._take_step": {
"total": 167.66447239697618,
"count": 63704,
"self": 4.995583342911232,
"children": {
"TorchPolicy.evaluate": {
"total": 162.66888905406495,
"count": 62550,
"self": 162.66888905406495
}
}
},
"workers": {
"total": 0.9422615168657558,
"count": 63704,
"self": 0.0,
"children": {
"worker_root": {
"total": 2188.82000029502,
"count": 63704,
"is_parallel": true,
"self": 968.597424694967,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020965329999853566,
"count": 1,
"is_parallel": true,
"self": 0.0006992569999511034,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013972760000342532,
"count": 8,
"is_parallel": true,
"self": 0.0013972760000342532
}
}
},
"UnityEnvironment.step": {
"total": 0.04838271900007385,
"count": 1,
"is_parallel": true,
"self": 0.0005304659998728312,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047647100018366473,
"count": 1,
"is_parallel": true,
"self": 0.00047647100018366473
},
"communicator.exchange": {
"total": 0.045778911000070366,
"count": 1,
"is_parallel": true,
"self": 0.045778911000070366
},
"steps_from_proto": {
"total": 0.0015968709999469866,
"count": 1,
"is_parallel": true,
"self": 0.00034579799989842286,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012510730000485637,
"count": 8,
"is_parallel": true,
"self": 0.0012510730000485637
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1220.2225756000528,
"count": 63703,
"is_parallel": true,
"self": 32.636756837107214,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.156360575962253,
"count": 63703,
"is_parallel": true,
"self": 23.156360575962253
},
"communicator.exchange": {
"total": 1065.340547949972,
"count": 63703,
"is_parallel": true,
"self": 1065.340547949972
},
"steps_from_proto": {
"total": 99.0889102370113,
"count": 63703,
"is_parallel": true,
"self": 20.71515891694139,
"children": {
"_process_rank_one_or_two_observation": {
"total": 78.37375132006991,
"count": 509624,
"is_parallel": true,
"self": 78.37375132006991
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 678.977256749947,
"count": 63704,
"self": 3.109648374903145,
"children": {
"process_trajectory": {
"total": 130.20481944504536,
"count": 63704,
"self": 130.00515822804527,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19966121700008443,
"count": 2,
"self": 0.19966121700008443
}
}
},
"_update_policy": {
"total": 545.6627889299984,
"count": 456,
"self": 300.0905897690018,
"children": {
"TorchPPOOptimizer.update": {
"total": 245.57219916099666,
"count": 22734,
"self": 245.57219916099666
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.069999578059651e-07,
"count": 1,
"self": 9.069999578059651e-07
},
"TrainerController._save_models": {
"total": 0.08519672900001751,
"count": 1,
"self": 0.0014517959998556762,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08374493300016184,
"count": 1,
"self": 0.08374493300016184
}
}
}
}
}
}
}