ppo-Pyramids / run_logs /timers.json
hossniper's picture
First Push
93f8de4 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.1395319402217865,
"min": 0.1332443207502365,
"max": 1.3979967832565308,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 4165.86572265625,
"min": 3937.63623046875,
"max": 42409.62890625,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999910.0,
"min": 29976.0,
"max": 2999910.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999910.0,
"min": 29976.0,
"max": 2999910.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7733352184295654,
"min": -0.08560027927160263,
"max": 0.8915632367134094,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 226.58721923828125,
"min": -20.800867080688477,
"max": 276.57586669921875,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.015415072441101074,
"min": -0.05110999569296837,
"max": 0.4439436197280884,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 4.516616344451904,
"min": -13.033048629760742,
"max": 105.65858459472656,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06936494483670685,
"min": 0.06343853837534581,
"max": 0.07512272979924914,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.971109227713896,
"min": 0.5066949313863758,
"max": 1.0749811925149213,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.0143866531621565,
"min": 0.00032094721586996527,
"max": 0.016064997132633114,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.201413144270191,
"min": 0.004172313806309548,
"max": 0.22583725649290537,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.5029637847595234e-06,
"min": 1.5029637847595234e-06,
"max": 0.0002984124576720381,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.1041492986633328e-05,
"min": 2.1041492986633328e-05,
"max": 0.0039691814769395335,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10050095476190476,
"min": 0.10050095476190476,
"max": 0.19947081904761907,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4070133666666667,
"min": 1.3962957333333335,
"max": 2.7976019666666674,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 6.004538071428571e-05,
"min": 6.004538071428571e-05,
"max": 0.009947134822857142,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0008406353299999999,
"min": 0.0008406353299999999,
"max": 0.13231374062,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.005969527643173933,
"min": 0.005815845914185047,
"max": 0.4347899854183197,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.08357338607311249,
"min": 0.08142184466123581,
"max": 3.043529987335205,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 226.6048387096774,
"min": 194.37333333333333,
"max": 999.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28099.0,
"min": 16519.0,
"max": 32774.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7733951435694773,
"min": -0.9998867181440194,
"max": 1.7932058645083624,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 219.90099780261517,
"min": -30.49640168994665,
"max": 268.84359791874886,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7733951435694773,
"min": -0.9998867181440194,
"max": 1.7932058645083624,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 219.90099780261517,
"min": -30.49640168994665,
"max": 268.84359791874886,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.014175843685617081,
"min": 0.012329076289461227,
"max": 8.713283972924247,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 1.757804617016518,
"min": 1.757804617016518,
"max": 148.1258275397122,
"count": 100
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1714196589",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714201695"
},
"total": 5105.946461957999,
"count": 1,
"self": 0.3730472319984983,
"children": {
"run_training.setup": {
"total": 0.05163312100012263,
"count": 1,
"self": 0.05163312100012263
},
"TrainerController.start_learning": {
"total": 5105.521781605001,
"count": 1,
"self": 3.9500788579935033,
"children": {
"TrainerController._reset_env": {
"total": 2.0374823630008905,
"count": 1,
"self": 2.0374823630008905
},
"TrainerController.advance": {
"total": 5099.4496216910065,
"count": 195596,
"self": 3.813167915338454,
"children": {
"env_step": {
"total": 3367.8976154028433,
"count": 195596,
"self": 3002.9066299311007,
"children": {
"SubprocessEnvManager._take_step": {
"total": 362.61245066682113,
"count": 195596,
"self": 13.184628681748109,
"children": {
"TorchPolicy.evaluate": {
"total": 349.427821985073,
"count": 187557,
"self": 349.427821985073
}
}
},
"workers": {
"total": 2.378534804921401,
"count": 195596,
"self": 0.0,
"children": {
"worker_root": {
"total": 5099.145722518225,
"count": 195596,
"is_parallel": true,
"self": 2387.3678608250657,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020960480005669524,
"count": 1,
"is_parallel": true,
"self": 0.0006656779987679329,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014303700017990195,
"count": 8,
"is_parallel": true,
"self": 0.0014303700017990195
}
}
},
"UnityEnvironment.step": {
"total": 0.03819867900074314,
"count": 1,
"is_parallel": true,
"self": 0.00042841800132009666,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00031373299952974776,
"count": 1,
"is_parallel": true,
"self": 0.00031373299952974776
},
"communicator.exchange": {
"total": 0.036307323000073666,
"count": 1,
"is_parallel": true,
"self": 0.036307323000073666
},
"steps_from_proto": {
"total": 0.0011492049998196308,
"count": 1,
"is_parallel": true,
"self": 0.0002544979988670093,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008947070009526215,
"count": 8,
"is_parallel": true,
"self": 0.0008947070009526215
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2711.777861693159,
"count": 195595,
"is_parallel": true,
"self": 64.49989337970146,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 42.915902133943746,
"count": 195595,
"is_parallel": true,
"self": 42.915902133943746
},
"communicator.exchange": {
"total": 2414.0309842529878,
"count": 195595,
"is_parallel": true,
"self": 2414.0309842529878
},
"steps_from_proto": {
"total": 190.33108192652617,
"count": 195595,
"is_parallel": true,
"self": 41.66293640749518,
"children": {
"_process_rank_one_or_two_observation": {
"total": 148.668145519031,
"count": 1564760,
"is_parallel": true,
"self": 148.668145519031
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1727.7388383728248,
"count": 195596,
"self": 7.999158218723096,
"children": {
"process_trajectory": {
"total": 354.5154791961313,
"count": 195596,
"self": 353.9802566671333,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5352225289980197,
"count": 6,
"self": 0.5352225289980197
}
}
},
"_update_policy": {
"total": 1365.2242009579704,
"count": 1401,
"self": 785.6171307617906,
"children": {
"TorchPPOOptimizer.update": {
"total": 579.6070701961798,
"count": 68382,
"self": 579.6070701961798
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.81999619398266e-07,
"count": 1,
"self": 9.81999619398266e-07
},
"TrainerController._save_models": {
"total": 0.08459771100024227,
"count": 1,
"self": 0.0015581249990646029,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08303958600117767,
"count": 1,
"self": 0.08303958600117767
}
}
}
}
}
}
}