ppo-Pyramids / run_logs /timers.json
Odohofre's picture
First Push
15c53f2 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.29657426476478577,
"min": 0.2897554337978363,
"max": 1.4350239038467407,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 8821.3046875,
"min": 8697.298828125,
"max": 43532.88671875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989910.0,
"min": 29952.0,
"max": 989910.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989910.0,
"min": 29952.0,
"max": 989910.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5784853100776672,
"min": -0.09496594220399857,
"max": 0.6881394982337952,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 161.97589111328125,
"min": -22.886791229248047,
"max": 196.80789184570312,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.029230307787656784,
"min": -0.001426962553523481,
"max": 0.6473596096038818,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 8.184486389160156,
"min": -0.39526861906051636,
"max": 153.42422485351562,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06566308649711401,
"min": 0.06492538236281169,
"max": 0.07467274950937275,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9192832109595961,
"min": 0.5227092465656092,
"max": 1.078447406281781,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016478244740158386,
"min": 0.002407533386232931,
"max": 0.018413000066809654,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.23069542636221738,
"min": 0.03226837781177791,
"max": 0.25778200093533515,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.717554570371427e-06,
"min": 7.717554570371427e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010804576398519999,
"min": 0.00010804576398519999,
"max": 0.0036340210886596997,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10257248571428572,
"min": 0.10257248571428572,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4360148000000001,
"min": 1.3886848,
"max": 2.6624488,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002669913228571429,
"min": 0.0002669913228571429,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00373787852,
"min": 0.00373787852,
"max": 0.12115289596999998,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.022908354178071022,
"min": 0.022908354178071022,
"max": 0.6109962463378906,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.3207169473171234,
"min": 0.3207169473171234,
"max": 4.276973724365234,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 316.1914893617021,
"min": 265.4684684684685,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29722.0,
"min": 15984.0,
"max": 33449.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.61996380445805,
"min": -1.0000000521540642,
"max": 1.680461235747144,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 152.2765976190567,
"min": -28.18000168353319,
"max": 186.531197167933,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.61996380445805,
"min": -1.0000000521540642,
"max": 1.680461235747144,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 152.2765976190567,
"min": -28.18000168353319,
"max": 186.531197167933,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.07497625435241795,
"min": 0.06435288020358777,
"max": 12.681969018653035,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 7.047767909127288,
"min": 6.827793399919756,
"max": 202.91150429844856,
"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": "1748797156",
"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": "1748799457"
},
"total": 2300.449025419,
"count": 1,
"self": 0.9095228479995967,
"children": {
"run_training.setup": {
"total": 0.01970977199994195,
"count": 1,
"self": 0.01970977199994195
},
"TrainerController.start_learning": {
"total": 2299.5197927990002,
"count": 1,
"self": 1.3121670219366024,
"children": {
"TrainerController._reset_env": {
"total": 2.333699991000003,
"count": 1,
"self": 2.333699991000003
},
"TrainerController.advance": {
"total": 2295.7477939720634,
"count": 64199,
"self": 1.3997954010019384,
"children": {
"env_step": {
"total": 1626.929686447049,
"count": 64199,
"self": 1478.5694860289268,
"children": {
"SubprocessEnvManager._take_step": {
"total": 147.57755988308486,
"count": 64199,
"self": 4.65705604710115,
"children": {
"TorchPolicy.evaluate": {
"total": 142.9205038359837,
"count": 62554,
"self": 142.9205038359837
}
}
},
"workers": {
"total": 0.7826405350374444,
"count": 64199,
"self": 0.0,
"children": {
"worker_root": {
"total": 2294.395025284994,
"count": 64199,
"is_parallel": true,
"self": 927.8244619679758,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019754929999180604,
"count": 1,
"is_parallel": true,
"self": 0.0006569980000676878,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013184949998503726,
"count": 8,
"is_parallel": true,
"self": 0.0013184949998503726
}
}
},
"UnityEnvironment.step": {
"total": 0.08331607200011604,
"count": 1,
"is_parallel": true,
"self": 0.000511123000023872,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00048405500001535984,
"count": 1,
"is_parallel": true,
"self": 0.00048405500001535984
},
"communicator.exchange": {
"total": 0.0806086669999786,
"count": 1,
"is_parallel": true,
"self": 0.0806086669999786
},
"steps_from_proto": {
"total": 0.0017122270000982098,
"count": 1,
"is_parallel": true,
"self": 0.00034319200017307594,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013690349999251339,
"count": 8,
"is_parallel": true,
"self": 0.0013690349999251339
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1366.5705633170182,
"count": 64198,
"is_parallel": true,
"self": 31.311321973051918,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.28051090203553,
"count": 64198,
"is_parallel": true,
"self": 23.28051090203553
},
"communicator.exchange": {
"total": 1216.2553685628818,
"count": 64198,
"is_parallel": true,
"self": 1216.2553685628818
},
"steps_from_proto": {
"total": 95.72336187904898,
"count": 64198,
"is_parallel": true,
"self": 19.123809269175354,
"children": {
"_process_rank_one_or_two_observation": {
"total": 76.59955260987363,
"count": 513584,
"is_parallel": true,
"self": 76.59955260987363
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 667.4183121240123,
"count": 64199,
"self": 2.6174271490588126,
"children": {
"process_trajectory": {
"total": 130.62156133395524,
"count": 64199,
"self": 130.36303837595528,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2585229579999577,
"count": 2,
"self": 0.2585229579999577
}
}
},
"_update_policy": {
"total": 534.1793236409983,
"count": 457,
"self": 298.8959639790005,
"children": {
"TorchPPOOptimizer.update": {
"total": 235.2833596619978,
"count": 22809,
"self": 235.2833596619978
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2760001482092775e-06,
"count": 1,
"self": 1.2760001482092775e-06
},
"TrainerController._save_models": {
"total": 0.12613053799987028,
"count": 1,
"self": 0.0016494379997311626,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12448110000013912,
"count": 1,
"self": 0.12448110000013912
}
}
}
}
}
}
}