Skanderbeg's picture
First Push
b2d7d0c
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4518812894821167,
"min": 0.45074206590652466,
"max": 1.4990878105163574,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 13729.9609375,
"min": 13327.541015625,
"max": 45476.328125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989908.0,
"min": 29952.0,
"max": 989908.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989908.0,
"min": 29952.0,
"max": 989908.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5348641276359558,
"min": -0.1015552282333374,
"max": 0.593877911567688,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 147.62249755859375,
"min": -24.373254776000977,
"max": 169.84909057617188,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.15492048859596252,
"min": -0.026511352509260178,
"max": 0.3356097340583801,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 42.758052825927734,
"min": -7.449689865112305,
"max": 80.88194274902344,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06585569595821046,
"min": 0.06451282698962889,
"max": 0.07744906780706437,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9219797434149464,
"min": 0.5421434746494506,
"max": 1.0798241030966962,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.017976974126733176,
"min": 0.00019669262060484336,
"max": 0.017976974126733176,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.25167763777426444,
"min": 0.002163618826653277,
"max": 0.25167763777426444,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.680997439699997e-06,
"min": 7.680997439699997e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010753396415579996,
"min": 0.00010753396415579996,
"max": 0.0036090483969839,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10256030000000001,
"min": 0.10256030000000001,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4358442,
"min": 1.3886848,
"max": 2.5030161000000004,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002657739699999999,
"min": 0.0002657739699999999,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0037208355799999986,
"min": 0.0037208355799999986,
"max": 0.12031130839000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.012005235068500042,
"min": 0.010883064940571785,
"max": 0.5256280899047852,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.16807329654693604,
"min": 0.1538080871105194,
"max": 3.679396629333496,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 367.7590361445783,
"min": 317.89473684210526,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30524.0,
"min": 15984.0,
"max": 33027.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5599325133195843,
"min": -1.0000000521540642,
"max": 1.6610484085584942,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 129.4743986055255,
"min": -30.99780160188675,
"max": 157.79959881305695,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5599325133195843,
"min": -1.0000000521540642,
"max": 1.6610484085584942,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 129.4743986055255,
"min": -30.99780160188675,
"max": 157.79959881305695,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04539550085763653,
"min": 0.03950958351350365,
"max": 10.569049447774887,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.767826571183832,
"min": 3.408212674607057,
"max": 169.1047911643982,
"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": "1685418293",
"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": "1685420380"
},
"total": 2086.782639508,
"count": 1,
"self": 0.6385111659997165,
"children": {
"run_training.setup": {
"total": 0.05721075799999653,
"count": 1,
"self": 0.05721075799999653
},
"TrainerController.start_learning": {
"total": 2086.0869175840003,
"count": 1,
"self": 1.2008564919970013,
"children": {
"TrainerController._reset_env": {
"total": 4.901953165999998,
"count": 1,
"self": 4.901953165999998
},
"TrainerController.advance": {
"total": 2079.894568028003,
"count": 63632,
"self": 1.2441181979443172,
"children": {
"env_step": {
"total": 1453.7481039020213,
"count": 63632,
"self": 1350.6756596020855,
"children": {
"SubprocessEnvManager._take_step": {
"total": 102.31691818098955,
"count": 63632,
"self": 4.556207602958182,
"children": {
"TorchPolicy.evaluate": {
"total": 97.76071057803136,
"count": 62579,
"self": 97.76071057803136
}
}
},
"workers": {
"total": 0.7555261189463636,
"count": 63632,
"self": 0.0,
"children": {
"worker_root": {
"total": 2081.744435219977,
"count": 63632,
"is_parallel": true,
"self": 837.5622645419439,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005820419000031052,
"count": 1,
"is_parallel": true,
"self": 0.0039026800000669937,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019177389999640582,
"count": 8,
"is_parallel": true,
"self": 0.0019177389999640582
}
}
},
"UnityEnvironment.step": {
"total": 0.045918260999997074,
"count": 1,
"is_parallel": true,
"self": 0.0005712640000297142,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005342810000001919,
"count": 1,
"is_parallel": true,
"self": 0.0005342810000001919
},
"communicator.exchange": {
"total": 0.042966065999962666,
"count": 1,
"is_parallel": true,
"self": 0.042966065999962666
},
"steps_from_proto": {
"total": 0.0018466500000045016,
"count": 1,
"is_parallel": true,
"self": 0.0004288729999757379,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014177770000287637,
"count": 8,
"is_parallel": true,
"self": 0.0014177770000287637
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1244.182170678033,
"count": 63631,
"is_parallel": true,
"self": 31.068775176077907,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 21.858514848009463,
"count": 63631,
"is_parallel": true,
"self": 21.858514848009463
},
"communicator.exchange": {
"total": 1097.2641642519714,
"count": 63631,
"is_parallel": true,
"self": 1097.2641642519714
},
"steps_from_proto": {
"total": 93.99071640197405,
"count": 63631,
"is_parallel": true,
"self": 18.97832291289359,
"children": {
"_process_rank_one_or_two_observation": {
"total": 75.01239348908047,
"count": 509048,
"is_parallel": true,
"self": 75.01239348908047
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 624.9023459280373,
"count": 63632,
"self": 2.3592838909977445,
"children": {
"process_trajectory": {
"total": 104.3104499170409,
"count": 63632,
"self": 104.09524181304124,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2152081039996574,
"count": 2,
"self": 0.2152081039996574
}
}
},
"_update_policy": {
"total": 518.2326121199987,
"count": 444,
"self": 333.35646919403666,
"children": {
"TorchPPOOptimizer.update": {
"total": 184.87614292596209,
"count": 22866,
"self": 184.87614292596209
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0160001693293452e-06,
"count": 1,
"self": 1.0160001693293452e-06
},
"TrainerController._save_models": {
"total": 0.08953888199994253,
"count": 1,
"self": 0.0012965079999958107,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08824237399994672,
"count": 1,
"self": 0.08824237399994672
}
}
}
}
}
}
}