gelas's picture
First Push
cce6465
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 1.4779021739959717,
"min": 1.4779021739959717,
"max": 1.4779021739959717,
"count": 1
},
"Pyramids.Policy.Entropy.sum": {
"value": 44833.640625,
"min": 44833.640625,
"max": 44833.640625,
"count": 1
},
"Pyramids.Step.mean": {
"value": 29952.0,
"min": 29952.0,
"max": 29952.0,
"count": 1
},
"Pyramids.Step.sum": {
"value": 29952.0,
"min": 29952.0,
"max": 29952.0,
"count": 1
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.1493891328573227,
"min": -0.1493891328573227,
"max": -0.1493891328573227,
"count": 1
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -35.40522384643555,
"min": -35.40522384643555,
"max": -35.40522384643555,
"count": 1
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.41453689336776733,
"min": 0.41453689336776733,
"max": 0.41453689336776733,
"count": 1
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 98.24524688720703,
"min": 98.24524688720703,
"max": 98.24524688720703,
"count": 1
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07245484556613202,
"min": 0.07245484556613202,
"max": 0.07245484556613202,
"count": 1
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.5071839189629241,
"min": 0.5071839189629241,
"max": 0.5071839189629241,
"count": 1
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.007853167407148429,
"min": 0.007853167407148429,
"max": 0.007853167407148429,
"count": 1
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.054972171850039,
"min": 0.054972171850039,
"max": 0.054972171850039,
"count": 1
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.00020301260375771423,
"min": 0.00020301260375771423,
"max": 0.00020301260375771423,
"count": 1
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0014210882263039997,
"min": 0.0014210882263039997,
"max": 0.0014210882263039997,
"count": 1
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.16767085714285712,
"min": 0.16767085714285712,
"max": 0.16767085714285712,
"count": 1
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.1736959999999999,
"min": 1.1736959999999999,
"max": 1.1736959999999999,
"count": 1
},
"Pyramids.Policy.Beta.mean": {
"value": 0.006770318628571428,
"min": 0.006770318628571428,
"max": 0.006770318628571428,
"count": 1
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0473922304,
"min": 0.0473922304,
"max": 0.0473922304,
"count": 1
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.4826365113258362,
"min": 0.4826365113258362,
"max": 0.4826365113258362,
"count": 1
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 3.378455638885498,
"min": 3.378455638885498,
"max": 3.378455638885498,
"count": 1
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 999.0,
"min": 999.0,
"max": 999.0,
"count": 1
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 15984.0,
"min": 15984.0,
"max": 15984.0,
"count": 1
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -1.0000000521540642,
"min": -1.0000000521540642,
"max": -1.0000000521540642,
"count": 1
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -16.000000834465027,
"min": -16.000000834465027,
"max": -16.000000834465027,
"count": 1
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -1.0000000521540642,
"min": -1.0000000521540642,
"max": -1.0000000521540642,
"count": 1
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -16.000000834465027,
"min": -16.000000834465027,
"max": -16.000000834465027,
"count": 1
},
"Pyramids.Policy.RndReward.mean": {
"value": 10.206843810155988,
"min": 10.206843810155988,
"max": 10.206843810155988,
"count": 1
},
"Pyramids.Policy.RndReward.sum": {
"value": 163.3095009624958,
"min": 163.3095009624958,
"max": 163.3095009624958,
"count": 1
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 1
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1680969150",
"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 /content/ml-agents/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": "1680969251"
},
"total": 100.38245255000015,
"count": 1,
"self": 0.4319502480002484,
"children": {
"run_training.setup": {
"total": 0.1863031289999526,
"count": 1,
"self": 0.1863031289999526
},
"TrainerController.start_learning": {
"total": 99.76419917299995,
"count": 1,
"self": 0.06670649799593775,
"children": {
"TrainerController._reset_env": {
"total": 4.07864030099995,
"count": 1,
"self": 4.07864030099995
},
"TrainerController.advance": {
"total": 95.50436213700391,
"count": 3128,
"self": 0.07213373600734485,
"children": {
"env_step": {
"total": 66.83853589900104,
"count": 3128,
"self": 61.30640775199572,
"children": {
"SubprocessEnvManager._take_step": {
"total": 5.491001821004147,
"count": 3128,
"self": 0.2410578490023454,
"children": {
"TorchPolicy.evaluate": {
"total": 5.249943972001802,
"count": 3128,
"self": 5.249943972001802
}
}
},
"workers": {
"total": 0.041126326001176494,
"count": 3128,
"self": 0.0,
"children": {
"worker_root": {
"total": 99.43050155100354,
"count": 3128,
"is_parallel": true,
"self": 43.90044527501118,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0024875469998733024,
"count": 1,
"is_parallel": true,
"self": 0.0007369399997969595,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001750607000076343,
"count": 8,
"is_parallel": true,
"self": 0.001750607000076343
}
}
},
"UnityEnvironment.step": {
"total": 0.08338808600001357,
"count": 1,
"is_parallel": true,
"self": 0.0006921489998603647,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00048398700005236606,
"count": 1,
"is_parallel": true,
"self": 0.00048398700005236606
},
"communicator.exchange": {
"total": 0.08051770800011582,
"count": 1,
"is_parallel": true,
"self": 0.08051770800011582
},
"steps_from_proto": {
"total": 0.0016942419999850244,
"count": 1,
"is_parallel": true,
"self": 0.00039491099937549734,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012993310006095271,
"count": 8,
"is_parallel": true,
"self": 0.0012993310006095271
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 55.530056275992365,
"count": 3127,
"is_parallel": true,
"self": 1.5922611750202122,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 1.1986585769907379,
"count": 3127,
"is_parallel": true,
"self": 1.1986585769907379
},
"communicator.exchange": {
"total": 47.94192702599116,
"count": 3127,
"is_parallel": true,
"self": 47.94192702599116
},
"steps_from_proto": {
"total": 4.797209497990252,
"count": 3127,
"is_parallel": true,
"self": 1.0486868099840194,
"children": {
"_process_rank_one_or_two_observation": {
"total": 3.748522688006233,
"count": 25016,
"is_parallel": true,
"self": 3.748522688006233
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 28.59369250199552,
"count": 3128,
"self": 0.08397289899448879,
"children": {
"process_trajectory": {
"total": 5.317397517001382,
"count": 3128,
"self": 5.317397517001382
},
"_update_policy": {
"total": 23.19232208599965,
"count": 12,
"self": 14.660075435000863,
"children": {
"TorchPPOOptimizer.update": {
"total": 8.532246650998786,
"count": 1125,
"self": 8.532246650998786
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.43000031838892e-07,
"count": 1,
"self": 9.43000031838892e-07
},
"TrainerController._save_models": {
"total": 0.11448929400012275,
"count": 1,
"self": 0.00143142800015994,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11305786599996281,
"count": 1,
"self": 0.11305786599996281
}
}
}
}
}
}
}