ying-zh's picture
First Push
ad68608
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.580917239189148,
"min": 0.580917239189148,
"max": 1.4421862363815308,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 17418.22265625,
"min": 17418.22265625,
"max": 43750.16015625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989993.0,
"min": 29952.0,
"max": 989993.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989993.0,
"min": 29952.0,
"max": 989993.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.3922484517097473,
"min": -0.09598099440336227,
"max": 0.3922484517097473,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 106.29933166503906,
"min": -23.131420135498047,
"max": 106.29933166503906,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.014985918998718262,
"min": -0.7901332974433899,
"max": 0.322534441947937,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 4.061183929443359,
"min": -207.01492309570312,
"max": 83.53642272949219,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0644482905714866,
"min": 0.0644482905714866,
"max": 0.07539407286969049,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9022760680008124,
"min": 0.5277585100878335,
"max": 1.0338281823302777,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01666902317798808,
"min": 0.0014207458754352392,
"max": 0.1697664340531143,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.23336632449183312,
"min": 0.016982112176821055,
"max": 2.5464965107967146,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.287183285257141e-06,
"min": 7.287183285257141e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010202056599359997,
"min": 0.00010202056599359997,
"max": 0.0036331528889491,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10242902857142858,
"min": 0.10242902857142858,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4340064000000001,
"min": 1.3886848,
"max": 2.6110509,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002526599542857143,
"min": 0.0002526599542857143,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0035372393599999996,
"min": 0.0035372393599999996,
"max": 0.12112398491,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009258979931473732,
"min": 0.007724926341325045,
"max": 0.4046212136745453,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.12962572276592255,
"min": 0.11243466287851334,
"max": 2.832348585128784,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 429.43055555555554,
"min": 429.43055555555554,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30919.0,
"min": 15984.0,
"max": 33416.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.4316610948493083,
"min": -1.0000000521540642,
"max": 1.4316610948493083,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 103.0795988291502,
"min": -30.420401625335217,
"max": 103.0795988291502,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.4316610948493083,
"min": -1.0000000521540642,
"max": 1.4316610948493083,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 103.0795988291502,
"min": -30.420401625335217,
"max": 103.0795988291502,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04097239354137451,
"min": 0.04097239354137451,
"max": 7.040461097843945,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.9500123349789646,
"min": 2.4994447205390316,
"max": 112.64737756550312,
"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": "1686233596",
"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": "1686235708"
},
"total": 2111.7924005679997,
"count": 1,
"self": 0.859832906999145,
"children": {
"run_training.setup": {
"total": 0.036305413000036424,
"count": 1,
"self": 0.036305413000036424
},
"TrainerController.start_learning": {
"total": 2110.8962622480003,
"count": 1,
"self": 1.2954607829287852,
"children": {
"TrainerController._reset_env": {
"total": 5.135314451999875,
"count": 1,
"self": 5.135314451999875
},
"TrainerController.advance": {
"total": 2104.3235457800715,
"count": 63511,
"self": 1.3124128900367396,
"children": {
"env_step": {
"total": 1472.8073344320128,
"count": 63511,
"self": 1367.216484554986,
"children": {
"SubprocessEnvManager._take_step": {
"total": 104.84429395404277,
"count": 63511,
"self": 4.575236113000983,
"children": {
"TorchPolicy.evaluate": {
"total": 100.26905784104179,
"count": 62553,
"self": 100.26905784104179
}
}
},
"workers": {
"total": 0.7465559229840437,
"count": 63511,
"self": 0.0,
"children": {
"worker_root": {
"total": 2106.4301822400703,
"count": 63511,
"is_parallel": true,
"self": 846.2108879140451,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018220140000266838,
"count": 1,
"is_parallel": true,
"self": 0.0005472210002608335,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012747929997658503,
"count": 8,
"is_parallel": true,
"self": 0.0012747929997658503
}
}
},
"UnityEnvironment.step": {
"total": 0.07348547899982805,
"count": 1,
"is_parallel": true,
"self": 0.0005761300001267955,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047679499994046637,
"count": 1,
"is_parallel": true,
"self": 0.00047679499994046637
},
"communicator.exchange": {
"total": 0.07055574399987563,
"count": 1,
"is_parallel": true,
"self": 0.07055574399987563
},
"steps_from_proto": {
"total": 0.001876809999885154,
"count": 1,
"is_parallel": true,
"self": 0.00039234399969245715,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014844660001926968,
"count": 8,
"is_parallel": true,
"self": 0.0014844660001926968
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1260.2192943260252,
"count": 63510,
"is_parallel": true,
"self": 32.54856881807564,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 21.93063140704453,
"count": 63510,
"is_parallel": true,
"self": 21.93063140704453
},
"communicator.exchange": {
"total": 1107.3259701049321,
"count": 63510,
"is_parallel": true,
"self": 1107.3259701049321
},
"steps_from_proto": {
"total": 98.41412399597289,
"count": 63510,
"is_parallel": true,
"self": 19.225226627914935,
"children": {
"_process_rank_one_or_two_observation": {
"total": 79.18889736805795,
"count": 508080,
"is_parallel": true,
"self": 79.18889736805795
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 630.2037984580218,
"count": 63511,
"self": 2.541849284028558,
"children": {
"process_trajectory": {
"total": 104.62664564898887,
"count": 63511,
"self": 104.37743398598877,
"children": {
"RLTrainer._checkpoint": {
"total": 0.24921166300009645,
"count": 2,
"self": 0.24921166300009645
}
}
},
"_update_policy": {
"total": 523.0353035250043,
"count": 454,
"self": 337.8870833949968,
"children": {
"TorchPPOOptimizer.update": {
"total": 185.14822013000753,
"count": 22785,
"self": 185.14822013000753
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3630001376441214e-06,
"count": 1,
"self": 1.3630001376441214e-06
},
"TrainerController._save_models": {
"total": 0.14193986999998742,
"count": 1,
"self": 0.001799349000066286,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14014052099992114,
"count": 1,
"self": 0.14014052099992114
}
}
}
}
}
}
}