Paperbag's picture
First Training of Pyramid
ac11d30
raw
history blame
No virus
19.2 kB
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3057468831539154,
"min": 0.2992863059043884,
"max": 1.4199155569076538,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 9284.9208984375,
"min": 8830.1435546875,
"max": 43074.55859375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989990.0,
"min": 29911.0,
"max": 989990.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989990.0,
"min": 29911.0,
"max": 989990.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.644329309463501,
"min": -0.07568545639514923,
"max": 0.7344602942466736,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 186.21116638183594,
"min": -18.315879821777344,
"max": 212.25901794433594,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.01729198731482029,
"min": 0.008747599087655544,
"max": 0.6061769723892212,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 4.997384071350098,
"min": 2.3268613815307617,
"max": 143.6639404296875,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06845470017067767,
"min": 0.0642113939268581,
"max": 0.07250552233225402,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9583658023894874,
"min": 0.48808322274714877,
"max": 1.0497878504033638,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016345883584783494,
"min": 0.0015995225304803943,
"max": 0.01853677334788732,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2288423701869689,
"min": 0.01926115628964468,
"max": 0.26566144272995496,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.607647464150002e-06,
"min": 7.607647464150002e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010650706449810003,
"min": 0.00010650706449810003,
"max": 0.0036340123886625993,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10253585000000001,
"min": 0.10253585000000001,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4355019000000002,
"min": 1.3886848,
"max": 2.6113374,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002633314150000001,
"min": 0.0002633314150000001,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036866398100000013,
"min": 0.0036866398100000013,
"max": 0.12115260626,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.012854060158133507,
"min": 0.012735738418996334,
"max": 0.6703988313674927,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1799568384885788,
"min": 0.1799568384885788,
"max": 4.692791938781738,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 290.96039603960395,
"min": 264.3193277310924,
"max": 990.4705882352941,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29387.0,
"min": 16838.0,
"max": 32894.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6891619767248631,
"min": -0.922475051600486,
"max": 1.731954527984966,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 168.9161976724863,
"min": -29.519201651215553,
"max": 200.54419798403978,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6891619767248631,
"min": -0.922475051600486,
"max": 1.731954527984966,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 168.9161976724863,
"min": -29.519201651215553,
"max": 200.54419798403978,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.0389627764661418,
"min": 0.03623296038681512,
"max": 13.453763642731834,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.8962776466141804,
"min": 3.81719197682105,
"max": 228.7139819264412,
"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": "1677943080",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.22.4",
"end_time_seconds": "1677945655"
},
"total": 2574.858164833,
"count": 1,
"self": 0.4465065169997615,
"children": {
"run_training.setup": {
"total": 0.12331867199998214,
"count": 1,
"self": 0.12331867199998214
},
"TrainerController.start_learning": {
"total": 2574.288339644,
"count": 1,
"self": 1.6770157880341685,
"children": {
"TrainerController._reset_env": {
"total": 10.503389657000014,
"count": 1,
"self": 10.503389657000014
},
"TrainerController.advance": {
"total": 2562.020171191966,
"count": 64283,
"self": 1.7971074189167666,
"children": {
"env_step": {
"total": 1786.3310924800444,
"count": 64283,
"self": 1658.5225831290154,
"children": {
"SubprocessEnvManager._take_step": {
"total": 126.79570753904096,
"count": 64283,
"self": 5.13502601000323,
"children": {
"TorchPolicy.evaluate": {
"total": 121.66068152903773,
"count": 62563,
"self": 41.675858372066784,
"children": {
"TorchPolicy.sample_actions": {
"total": 79.98482315697095,
"count": 62563,
"self": 79.98482315697095
}
}
}
}
},
"workers": {
"total": 1.0128018119881403,
"count": 64283,
"self": 0.0,
"children": {
"worker_root": {
"total": 2568.2508695279976,
"count": 64283,
"is_parallel": true,
"self": 1040.5518346049776,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005200208999951883,
"count": 1,
"is_parallel": true,
"self": 0.004005081999991944,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001195126999959939,
"count": 8,
"is_parallel": true,
"self": 0.001195126999959939
}
}
},
"UnityEnvironment.step": {
"total": 0.10467095800004245,
"count": 1,
"is_parallel": true,
"self": 0.0005545550000078947,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047238500002322326,
"count": 1,
"is_parallel": true,
"self": 0.00047238500002322326
},
"communicator.exchange": {
"total": 0.10194681600000877,
"count": 1,
"is_parallel": true,
"self": 0.10194681600000877
},
"steps_from_proto": {
"total": 0.0016972020000025623,
"count": 1,
"is_parallel": true,
"self": 0.00041512900003226605,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012820729999702962,
"count": 8,
"is_parallel": true,
"self": 0.0012820729999702962
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1527.69903492302,
"count": 64282,
"is_parallel": true,
"self": 34.328156391015,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.092370921971053,
"count": 64282,
"is_parallel": true,
"self": 24.092370921971053
},
"communicator.exchange": {
"total": 1370.5423468710242,
"count": 64282,
"is_parallel": true,
"self": 1370.5423468710242
},
"steps_from_proto": {
"total": 98.7361607390099,
"count": 64282,
"is_parallel": true,
"self": 24.23473222695185,
"children": {
"_process_rank_one_or_two_observation": {
"total": 74.50142851205806,
"count": 514256,
"is_parallel": true,
"self": 74.50142851205806
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 773.8919712930046,
"count": 64283,
"self": 3.136644695975292,
"children": {
"process_trajectory": {
"total": 172.51422036102798,
"count": 64283,
"self": 172.31861129202792,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19560906900005648,
"count": 2,
"self": 0.19560906900005648
}
}
},
"_update_policy": {
"total": 598.2411062360013,
"count": 456,
"self": 228.6747151009729,
"children": {
"TorchPPOOptimizer.update": {
"total": 369.5663911350284,
"count": 22806,
"self": 369.5663911350284
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5529999473073985e-06,
"count": 1,
"self": 1.5529999473073985e-06
},
"TrainerController._save_models": {
"total": 0.08776145400042878,
"count": 1,
"self": 0.0015321450005103543,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08622930899991843,
"count": 1,
"self": 0.08622930899991843
}
}
}
}
}
}
}