ppo-PyramidsRND / run_logs /timers.json
ericalt's picture
First Push
1623ff8
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4067290127277374,
"min": 0.40045079588890076,
"max": 1.3629783391952515,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12266.947265625,
"min": 11853.34375,
"max": 41347.3125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989907.0,
"min": 29952.0,
"max": 989907.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989907.0,
"min": 29952.0,
"max": 989907.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6101654767990112,
"min": -0.09352421760559082,
"max": 0.653337299823761,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 172.6768341064453,
"min": -22.539337158203125,
"max": 184.24111938476562,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.03593563660979271,
"min": -0.01401680801063776,
"max": 0.6019686460494995,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 10.169785499572754,
"min": -3.686420440673828,
"max": 142.66656494140625,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07045643438219226,
"min": 0.06578616291101623,
"max": 0.07211404215527832,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9863900813506916,
"min": 0.5035267084135792,
"max": 1.0708148273988627,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016589475150491733,
"min": 0.0004592787752315578,
"max": 0.020815455152433132,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.23225265210688426,
"min": 0.006429902853241809,
"max": 0.23970152667493047,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.590483184157144e-06,
"min": 7.590483184157144e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010626676457820002,
"min": 0.00010626676457820002,
"max": 0.0035079500306833995,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1025301285714286,
"min": 0.1025301285714286,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4354218000000003,
"min": 1.3886848,
"max": 2.5693166,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002627598442857144,
"min": 0.0002627598442857144,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036786378200000017,
"min": 0.0036786378200000017,
"max": 0.11695472834,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.012438023462891579,
"min": 0.012438023462891579,
"max": 0.7507800459861755,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1741323322057724,
"min": 0.1741323322057724,
"max": 5.255460262298584,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 302.9,
"min": 288.27450980392155,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30290.0,
"min": 15984.0,
"max": 34269.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6965454360752394,
"min": -1.0000000521540642,
"max": 1.6965454360752394,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 167.9579981714487,
"min": -30.564401663839817,
"max": 170.99279782176018,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6965454360752394,
"min": -1.0000000521540642,
"max": 1.6965454360752394,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 167.9579981714487,
"min": -30.564401663839817,
"max": 170.99279782176018,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03903078017027277,
"min": 0.03903078017027277,
"max": 16.02445948496461,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.8640472368570045,
"min": 3.8384932982735336,
"max": 256.39135175943375,
"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": "1685238032",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1685240209"
},
"total": 2176.1195678999998,
"count": 1,
"self": 0.7984674679992168,
"children": {
"run_training.setup": {
"total": 0.03708921400038889,
"count": 1,
"self": 0.03708921400038889
},
"TrainerController.start_learning": {
"total": 2175.284011218,
"count": 1,
"self": 1.2600989219913572,
"children": {
"TrainerController._reset_env": {
"total": 4.260292400000253,
"count": 1,
"self": 4.260292400000253
},
"TrainerController.advance": {
"total": 2169.620339670008,
"count": 63981,
"self": 1.3018363320866229,
"children": {
"env_step": {
"total": 1548.0446831979193,
"count": 63981,
"self": 1443.70891991795,
"children": {
"SubprocessEnvManager._take_step": {
"total": 103.59430446602846,
"count": 63981,
"self": 4.618165824884727,
"children": {
"TorchPolicy.evaluate": {
"total": 98.97613864114373,
"count": 62547,
"self": 98.97613864114373
}
}
},
"workers": {
"total": 0.7414588139408806,
"count": 63981,
"self": 0.0,
"children": {
"worker_root": {
"total": 2170.225279885,
"count": 63981,
"is_parallel": true,
"self": 833.8042621638783,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018456980001246848,
"count": 1,
"is_parallel": true,
"self": 0.0005734580008720513,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012722399992526334,
"count": 8,
"is_parallel": true,
"self": 0.0012722399992526334
}
}
},
"UnityEnvironment.step": {
"total": 0.07047235699974408,
"count": 1,
"is_parallel": true,
"self": 0.0005886129993086797,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047862500014161924,
"count": 1,
"is_parallel": true,
"self": 0.00047862500014161924
},
"communicator.exchange": {
"total": 0.06758129600029861,
"count": 1,
"is_parallel": true,
"self": 0.06758129600029861
},
"steps_from_proto": {
"total": 0.0018238229999951727,
"count": 1,
"is_parallel": true,
"self": 0.00035315899913257454,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014706640008625982,
"count": 8,
"is_parallel": true,
"self": 0.0014706640008625982
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1336.4210177211216,
"count": 63980,
"is_parallel": true,
"self": 31.07096269902604,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.021756299118806,
"count": 63980,
"is_parallel": true,
"self": 22.021756299118806
},
"communicator.exchange": {
"total": 1187.5475199359716,
"count": 63980,
"is_parallel": true,
"self": 1187.5475199359716
},
"steps_from_proto": {
"total": 95.78077878700515,
"count": 63980,
"is_parallel": true,
"self": 19.237009196297095,
"children": {
"_process_rank_one_or_two_observation": {
"total": 76.54376959070805,
"count": 511840,
"is_parallel": true,
"self": 76.54376959070805
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 620.273820140002,
"count": 63981,
"self": 2.4047824878653046,
"children": {
"process_trajectory": {
"total": 106.22263575613624,
"count": 63981,
"self": 105.9611806941366,
"children": {
"RLTrainer._checkpoint": {
"total": 0.26145506199964075,
"count": 2,
"self": 0.26145506199964075
}
}
},
"_update_policy": {
"total": 511.6464018960005,
"count": 449,
"self": 329.38463720500295,
"children": {
"TorchPPOOptimizer.update": {
"total": 182.26176469099755,
"count": 22836,
"self": 182.26176469099755
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1550000635907054e-06,
"count": 1,
"self": 1.1550000635907054e-06
},
"TrainerController._save_models": {
"total": 0.14327907100050652,
"count": 1,
"self": 0.0018795120004142518,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14139955900009227,
"count": 1,
"self": 0.14139955900009227
}
}
}
}
}
}
}