Augcos's picture
first commit
f743af0
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3521389067173004,
"min": 0.34519991278648376,
"max": 1.3896154165267944,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 10513.458984375,
"min": 10367.0439453125,
"max": 42155.375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989919.0,
"min": 29952.0,
"max": 989919.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989919.0,
"min": 29952.0,
"max": 989919.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6310458779335022,
"min": -0.07969990372657776,
"max": 0.6310458779335022,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 180.4791259765625,
"min": -19.287376403808594,
"max": 180.4791259765625,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.0034922054037451744,
"min": 0.0034922054037451744,
"max": 0.45592746138572693,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 0.9987707734107971,
"min": 0.9987707734107971,
"max": 110.18476867675781,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06813933882710914,
"min": 0.06472213544443042,
"max": 0.07374232479284784,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.022090082406637,
"min": 0.5051257857497871,
"max": 1.0839414828612162,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016946484297940056,
"min": 0.0012775651862379082,
"max": 0.01716882213513192,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.25419726446910085,
"min": 0.015330782234854897,
"max": 0.25419726446910085,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.539337486919999e-06,
"min": 7.539337486919999e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011309006230379998,
"min": 0.00011309006230379998,
"max": 0.0033797099734300994,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10251308,
"min": 0.10251308,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5376962,
"min": 1.3886848,
"max": 2.5265699,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002610566919999999,
"min": 0.0002610566919999999,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003915850379999999,
"min": 0.003915850379999999,
"max": 0.11268433300999997,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.017882514744997025,
"min": 0.017882514744997025,
"max": 0.679629385471344,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.2682377099990845,
"min": 0.25400763750076294,
"max": 4.757405757904053,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 296.36893203883494,
"min": 296.36893203883494,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30526.0,
"min": 15984.0,
"max": 33745.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7040672882531698,
"min": -1.0000000521540642,
"max": 1.7040672882531698,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 177.22299797832966,
"min": -25.947401702404022,
"max": 177.22299797832966,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7040672882531698,
"min": -1.0000000521540642,
"max": 1.7040672882531698,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 177.22299797832966,
"min": -25.947401702404022,
"max": 177.22299797832966,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.05472138139423176,
"min": 0.05472138139423176,
"max": 13.125991547480226,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 5.6910236650001025,
"min": 5.350166652817279,
"max": 210.0158647596836,
"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": "1681207901",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1681210070"
},
"total": 2168.690775298,
"count": 1,
"self": 0.5079208060001292,
"children": {
"run_training.setup": {
"total": 0.16960689400002593,
"count": 1,
"self": 0.16960689400002593
},
"TrainerController.start_learning": {
"total": 2168.013247598,
"count": 1,
"self": 1.4123368669875163,
"children": {
"TrainerController._reset_env": {
"total": 4.691571126000099,
"count": 1,
"self": 4.691571126000099
},
"TrainerController.advance": {
"total": 2161.8154079500123,
"count": 63998,
"self": 1.5507963239742821,
"children": {
"env_step": {
"total": 1553.6725388239938,
"count": 63998,
"self": 1444.960617174958,
"children": {
"SubprocessEnvManager._take_step": {
"total": 107.85180147296967,
"count": 63998,
"self": 4.909793793979588,
"children": {
"TorchPolicy.evaluate": {
"total": 102.94200767899008,
"count": 62559,
"self": 102.94200767899008
}
}
},
"workers": {
"total": 0.8601201760660615,
"count": 63998,
"self": 0.0,
"children": {
"worker_root": {
"total": 2162.929735082025,
"count": 63998,
"is_parallel": true,
"self": 832.09142663799,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005264933000034944,
"count": 1,
"is_parallel": true,
"self": 0.003825734999850283,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014391980001846605,
"count": 8,
"is_parallel": true,
"self": 0.0014391980001846605
}
}
},
"UnityEnvironment.step": {
"total": 0.04928018099997189,
"count": 1,
"is_parallel": true,
"self": 0.0005231169999433405,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005031590000044162,
"count": 1,
"is_parallel": true,
"self": 0.0005031590000044162
},
"communicator.exchange": {
"total": 0.0465171810000129,
"count": 1,
"is_parallel": true,
"self": 0.0465171810000129
},
"steps_from_proto": {
"total": 0.001736724000011236,
"count": 1,
"is_parallel": true,
"self": 0.0005070760000762675,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012296479999349685,
"count": 8,
"is_parallel": true,
"self": 0.0012296479999349685
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1330.8383084440352,
"count": 63997,
"is_parallel": true,
"self": 32.54106370399677,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.723026234016174,
"count": 63997,
"is_parallel": true,
"self": 23.723026234016174
},
"communicator.exchange": {
"total": 1176.4424775600387,
"count": 63997,
"is_parallel": true,
"self": 1176.4424775600387
},
"steps_from_proto": {
"total": 98.13174094598355,
"count": 63997,
"is_parallel": true,
"self": 21.02078827297396,
"children": {
"_process_rank_one_or_two_observation": {
"total": 77.11095267300959,
"count": 511976,
"is_parallel": true,
"self": 77.11095267300959
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 606.5920728020443,
"count": 63998,
"self": 2.6507581989922073,
"children": {
"process_trajectory": {
"total": 109.71460714005218,
"count": 63998,
"self": 109.44500459805215,
"children": {
"RLTrainer._checkpoint": {
"total": 0.26960254200002964,
"count": 2,
"self": 0.26960254200002964
}
}
},
"_update_policy": {
"total": 494.2267074629999,
"count": 451,
"self": 316.0622336389696,
"children": {
"TorchPPOOptimizer.update": {
"total": 178.16447382403032,
"count": 22788,
"self": 178.16447382403032
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.40000063565094e-07,
"count": 1,
"self": 9.40000063565094e-07
},
"TrainerController._save_models": {
"total": 0.09393071499971484,
"count": 1,
"self": 0.0013310619997355388,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0925996529999793,
"count": 1,
"self": 0.0925996529999793
}
}
}
}
}
}
}