nondevs's picture
First Push
07f3349
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5866684317588806,
"min": 0.5866684317588806,
"max": 1.4416086673736572,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 17637.599609375,
"min": 17637.599609375,
"max": 43732.640625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989965.0,
"min": 29952.0,
"max": 989965.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989965.0,
"min": 29952.0,
"max": 989965.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.23244169354438782,
"min": -0.0936233252286911,
"max": 0.2532021999359131,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 59.50507354736328,
"min": -22.563220977783203,
"max": 64.33224487304688,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.0027967700734734535,
"min": -0.005371594335883856,
"max": 0.4136130213737488,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 0.7159731388092041,
"min": -1.3321553468704224,
"max": 98.02628326416016,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06816870182852394,
"min": 0.06612187482131135,
"max": 0.07319915672304064,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9543618255993351,
"min": 0.4855297229670245,
"max": 1.079226849446023,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.00830701172050058,
"min": 6.267583174525404e-05,
"max": 0.00908947610090921,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.11629816408700813,
"min": 0.0008774616444335566,
"max": 0.12725266541272895,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.592840326228573e-06,
"min": 7.592840326228573e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010629976456720002,
"min": 0.00010629976456720002,
"max": 0.0033312204895931995,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10253091428571429,
"min": 0.10253091428571429,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4354328,
"min": 1.3691136000000002,
"max": 2.4847116,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002628383371428572,
"min": 0.0002628383371428572,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036797367200000005,
"min": 0.0036797367200000005,
"max": 0.11104963931999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.011022587306797504,
"min": 0.011022587306797504,
"max": 0.3945649564266205,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.15431621670722961,
"min": 0.15431621670722961,
"max": 2.7619547843933105,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 597.3469387755102,
"min": 595.811320754717,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29270.0,
"min": 15984.0,
"max": 32545.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.0351836346850103,
"min": -1.0000000521540642,
"max": 1.0351836346850103,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 50.723998099565506,
"min": -32.000001668930054,
"max": 51.05739839375019,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.0351836346850103,
"min": -1.0000000521540642,
"max": 1.0351836346850103,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 50.723998099565506,
"min": -32.000001668930054,
"max": 51.05739839375019,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.06859852834509647,
"min": 0.06845270992626491,
"max": 7.586557001806796,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.3613278889097273,
"min": 3.3613278889097273,
"max": 121.38491202890873,
"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": "1699695986",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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 --force",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1699698127"
},
"total": 2141.355398103,
"count": 1,
"self": 0.5395645509997848,
"children": {
"run_training.setup": {
"total": 0.04326383700004044,
"count": 1,
"self": 0.04326383700004044
},
"TrainerController.start_learning": {
"total": 2140.772569715,
"count": 1,
"self": 1.309254462939407,
"children": {
"TrainerController._reset_env": {
"total": 4.836617509000007,
"count": 1,
"self": 4.836617509000007
},
"TrainerController.advance": {
"total": 2134.5547667050605,
"count": 63324,
"self": 1.396024338108873,
"children": {
"env_step": {
"total": 1475.582709613979,
"count": 63324,
"self": 1345.6727412790424,
"children": {
"SubprocessEnvManager._take_step": {
"total": 129.1461458479962,
"count": 63324,
"self": 4.687967208042892,
"children": {
"TorchPolicy.evaluate": {
"total": 124.4581786399533,
"count": 62563,
"self": 124.4581786399533
}
}
},
"workers": {
"total": 0.7638224869403984,
"count": 63324,
"self": 0.0,
"children": {
"worker_root": {
"total": 2136.4262111780167,
"count": 63324,
"is_parallel": true,
"self": 907.8826829870036,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0024707600000510865,
"count": 1,
"is_parallel": true,
"self": 0.0006737679998423118,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017969920002087747,
"count": 8,
"is_parallel": true,
"self": 0.0017969920002087747
}
}
},
"UnityEnvironment.step": {
"total": 0.05053177900003902,
"count": 1,
"is_parallel": true,
"self": 0.0006370119999701274,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004577970000809728,
"count": 1,
"is_parallel": true,
"self": 0.0004577970000809728
},
"communicator.exchange": {
"total": 0.047755452000046716,
"count": 1,
"is_parallel": true,
"self": 0.047755452000046716
},
"steps_from_proto": {
"total": 0.0016815179999412067,
"count": 1,
"is_parallel": true,
"self": 0.00035876600031770067,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001322751999623506,
"count": 8,
"is_parallel": true,
"self": 0.001322751999623506
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1228.5435281910131,
"count": 63323,
"is_parallel": true,
"self": 33.89693297411486,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.09137851196283,
"count": 63323,
"is_parallel": true,
"self": 23.09137851196283
},
"communicator.exchange": {
"total": 1076.641008239979,
"count": 63323,
"is_parallel": true,
"self": 1076.641008239979
},
"steps_from_proto": {
"total": 94.91420846495635,
"count": 63323,
"is_parallel": true,
"self": 18.470260686111942,
"children": {
"_process_rank_one_or_two_observation": {
"total": 76.4439477788444,
"count": 506584,
"is_parallel": true,
"self": 76.4439477788444
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 657.5760327529727,
"count": 63324,
"self": 2.4414413270676505,
"children": {
"process_trajectory": {
"total": 125.45182186689908,
"count": 63324,
"self": 125.20698278989857,
"children": {
"RLTrainer._checkpoint": {
"total": 0.24483907700050622,
"count": 2,
"self": 0.24483907700050622
}
}
},
"_update_policy": {
"total": 529.6827695590059,
"count": 444,
"self": 322.38874303800117,
"children": {
"TorchPPOOptimizer.update": {
"total": 207.29402652100475,
"count": 22806,
"self": 207.29402652100475
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.189998309011571e-07,
"count": 1,
"self": 9.189998309011571e-07
},
"TrainerController._save_models": {
"total": 0.07193011900017154,
"count": 1,
"self": 0.001651045000016893,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07027907400015465,
"count": 1,
"self": 0.07027907400015465
}
}
}
}
}
}
}