ppo-PyramidsRND / run_logs /timers.json
mnneely's picture
First Push
e01b4da verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.29375311732292175,
"min": 0.2765669524669647,
"max": 1.3184360265731812,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 8850.1943359375,
"min": 8332.4091796875,
"max": 39996.07421875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989903.0,
"min": 29980.0,
"max": 989903.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989903.0,
"min": 29980.0,
"max": 989903.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6412670016288757,
"min": -0.09725351631641388,
"max": 0.6521226763725281,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 185.96742248535156,
"min": -23.27002716064453,
"max": 185.96742248535156,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.010980808176100254,
"min": 0.010342489928007126,
"max": 0.3614236116409302,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 3.184434413909912,
"min": 2.895897150039673,
"max": 86.0188217163086,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06943361630103376,
"min": 0.06394634582795247,
"max": 0.07323762636450773,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9720706282144725,
"min": 0.5681256309270311,
"max": 1.0360873635760144,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016681260921835753,
"min": 0.0005471312916094773,
"max": 0.016920212806952703,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.23353765290570055,
"min": 0.00601844420770425,
"max": 0.25380319210429053,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.285833285707139e-06,
"min": 7.285833285707139e-06,
"max": 0.00029522445159185,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010200166599989994,
"min": 0.00010200166599989994,
"max": 0.0034923604358799,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10242857857142858,
"min": 0.10242857857142858,
"max": 0.19840815,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4340001,
"min": 1.4340001,
"max": 2.4847311,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025261499928571414,
"min": 0.00025261499928571414,
"max": 0.009840974185,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0035366099899999982,
"min": 0.0035366099899999982,
"max": 0.11642559799,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.013293005526065826,
"min": 0.012879446148872375,
"max": 0.5006797313690186,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.18610207736492157,
"min": 0.18031224608421326,
"max": 4.005437850952148,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 290.47115384615387,
"min": 290.47115384615387,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30209.0,
"min": 15884.0,
"max": 32623.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6909485574279512,
"min": -1.0000000521540642,
"max": 1.6909485574279512,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 177.54959852993488,
"min": -32.000001668930054,
"max": 177.54959852993488,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6909485574279512,
"min": -1.0000000521540642,
"max": 1.6909485574279512,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 177.54959852993488,
"min": -32.000001668930054,
"max": 177.54959852993488,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.040130889611776056,
"min": 0.040130889611776056,
"max": 10.522159930085763,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.213743409236486,
"min": 3.9007105811906513,
"max": 168.3545588813722,
"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": "1725988624",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1725990959"
},
"total": 2335.432020221,
"count": 1,
"self": 0.4765931970005113,
"children": {
"run_training.setup": {
"total": 0.051869903000124395,
"count": 1,
"self": 0.051869903000124395
},
"TrainerController.start_learning": {
"total": 2334.9035571209997,
"count": 1,
"self": 1.513143773965112,
"children": {
"TrainerController._reset_env": {
"total": 1.920563138000034,
"count": 1,
"self": 1.920563138000034
},
"TrainerController.advance": {
"total": 2331.3693693800346,
"count": 63995,
"self": 1.5656247089523276,
"children": {
"env_step": {
"total": 1631.3215734170506,
"count": 63995,
"self": 1471.082039843119,
"children": {
"SubprocessEnvManager._take_step": {
"total": 159.344604555999,
"count": 63995,
"self": 4.666989141933527,
"children": {
"TorchPolicy.evaluate": {
"total": 154.67761541406549,
"count": 62572,
"self": 154.67761541406549
}
}
},
"workers": {
"total": 0.8949290179325544,
"count": 63995,
"self": 0.0,
"children": {
"worker_root": {
"total": 2329.522894046048,
"count": 63995,
"is_parallel": true,
"self": 981.6756345020501,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00199566300011611,
"count": 1,
"is_parallel": true,
"self": 0.0005921090000811091,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001403554000035001,
"count": 8,
"is_parallel": true,
"self": 0.001403554000035001
}
}
},
"UnityEnvironment.step": {
"total": 0.09446677899995848,
"count": 1,
"is_parallel": true,
"self": 0.0006791299999804323,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000536589999910575,
"count": 1,
"is_parallel": true,
"self": 0.000536589999910575
},
"communicator.exchange": {
"total": 0.09034355599987975,
"count": 1,
"is_parallel": true,
"self": 0.09034355599987975
},
"steps_from_proto": {
"total": 0.0029075030001877167,
"count": 1,
"is_parallel": true,
"self": 0.0012089930007732619,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016985099994144548,
"count": 8,
"is_parallel": true,
"self": 0.0016985099994144548
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1347.8472595439978,
"count": 63994,
"is_parallel": true,
"self": 33.965879150846376,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.506049637064052,
"count": 63994,
"is_parallel": true,
"self": 22.506049637064052
},
"communicator.exchange": {
"total": 1193.586287892993,
"count": 63994,
"is_parallel": true,
"self": 1193.586287892993
},
"steps_from_proto": {
"total": 97.78904286309444,
"count": 63994,
"is_parallel": true,
"self": 20.464883503239662,
"children": {
"_process_rank_one_or_two_observation": {
"total": 77.32415935985478,
"count": 511952,
"is_parallel": true,
"self": 77.32415935985478
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 698.4821712540318,
"count": 63995,
"self": 2.796585341112859,
"children": {
"process_trajectory": {
"total": 136.70537500592627,
"count": 63995,
"self": 136.29073822792634,
"children": {
"RLTrainer._checkpoint": {
"total": 0.41463677799993093,
"count": 2,
"self": 0.41463677799993093
}
}
},
"_update_policy": {
"total": 558.9802109069926,
"count": 452,
"self": 315.2587095859599,
"children": {
"TorchPPOOptimizer.update": {
"total": 243.72150132103275,
"count": 22797,
"self": 243.72150132103275
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1040001481887884e-06,
"count": 1,
"self": 1.1040001481887884e-06
},
"TrainerController._save_models": {
"total": 0.10047972499978641,
"count": 1,
"self": 0.0013463329996739049,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09913339200011251,
"count": 1,
"self": 0.09913339200011251
}
}
}
}
}
}
}