Mihara-bot's picture
First Push
5d478a1
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.507186770439148,
"min": 0.507186770439148,
"max": 1.4969267845153809,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 15199.3740234375,
"min": 15199.3740234375,
"max": 45410.76953125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989912.0,
"min": 29952.0,
"max": 989912.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989912.0,
"min": 29952.0,
"max": 989912.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5953932404518127,
"min": -0.09924907237291336,
"max": 0.5979040265083313,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 166.11471557617188,
"min": -24.01827621459961,
"max": 171.00054931640625,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.016802415251731873,
"min": 0.011869003996253014,
"max": 0.5212312340736389,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 4.687873840332031,
"min": 3.2639760971069336,
"max": 125.09549713134766,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07036214948831392,
"min": 0.06699535402422163,
"max": 0.0752343580264683,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9850700928363949,
"min": 0.5266405061852781,
"max": 1.075466328730245,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016287839223791487,
"min": 0.0013945435204176435,
"max": 0.02288176068838194,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22802974913308083,
"min": 0.01952360928584701,
"max": 0.25914964200609236,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.288404713421424e-06,
"min": 7.288404713421424e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010203766598789995,
"min": 0.00010203766598789995,
"max": 0.003633292388902599,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10242943571428573,
"min": 0.10242943571428573,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4340121000000001,
"min": 1.3886848,
"max": 2.6110974000000002,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025270062785714276,
"min": 0.00025270062785714276,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0035378087899999985,
"min": 0.0035378087899999985,
"max": 0.12112863026000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.013793171383440495,
"min": 0.013613351620733738,
"max": 0.7294358015060425,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.19310440123081207,
"min": 0.19310440123081207,
"max": 5.106050491333008,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 300.5,
"min": 300.5,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28247.0,
"min": 15984.0,
"max": 32347.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.637724190715112,
"min": -1.0000000521540642,
"max": 1.637724190715112,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 155.58379811793566,
"min": -29.97000166028738,
"max": 157.81759797036648,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.637724190715112,
"min": -1.0000000521540642,
"max": 1.637724190715112,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 155.58379811793566,
"min": -29.97000166028738,
"max": 157.81759797036648,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04249632140823738,
"min": 0.04249632140823738,
"max": 16.90289930999279,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.037150533782551,
"min": 4.037150533782551,
"max": 270.44638895988464,
"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": "1681033717",
"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 ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
"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": "1681035770"
},
"total": 2053.224197388,
"count": 1,
"self": 0.8473793639996074,
"children": {
"run_training.setup": {
"total": 0.10853199799998947,
"count": 1,
"self": 0.10853199799998947
},
"TrainerController.start_learning": {
"total": 2052.268286026,
"count": 1,
"self": 1.2555110019843596,
"children": {
"TrainerController._reset_env": {
"total": 3.722589626999934,
"count": 1,
"self": 3.722589626999934
},
"TrainerController.advance": {
"total": 2047.1488231750159,
"count": 63881,
"self": 1.3056641149407824,
"children": {
"env_step": {
"total": 1439.8565127580207,
"count": 63881,
"self": 1338.4554458420341,
"children": {
"SubprocessEnvManager._take_step": {
"total": 100.65049187801992,
"count": 63881,
"self": 4.466481268051211,
"children": {
"TorchPolicy.evaluate": {
"total": 96.18401060996871,
"count": 62561,
"self": 96.18401060996871
}
}
},
"workers": {
"total": 0.7505750379666551,
"count": 63881,
"self": 0.0,
"children": {
"worker_root": {
"total": 2047.4948656249692,
"count": 63881,
"is_parallel": true,
"self": 813.8907002189471,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0016704929998923035,
"count": 1,
"is_parallel": true,
"self": 0.0005305350000526232,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011399579998396803,
"count": 8,
"is_parallel": true,
"self": 0.0011399579998396803
}
}
},
"UnityEnvironment.step": {
"total": 0.04978258200003438,
"count": 1,
"is_parallel": true,
"self": 0.0007885850000093342,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004911470000479312,
"count": 1,
"is_parallel": true,
"self": 0.0004911470000479312
},
"communicator.exchange": {
"total": 0.046569432000069355,
"count": 1,
"is_parallel": true,
"self": 0.046569432000069355
},
"steps_from_proto": {
"total": 0.0019334179999077605,
"count": 1,
"is_parallel": true,
"self": 0.00043845900017913664,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001494958999728624,
"count": 8,
"is_parallel": true,
"self": 0.001494958999728624
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1233.604165406022,
"count": 63880,
"is_parallel": true,
"self": 31.79017794296942,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.73642719901227,
"count": 63880,
"is_parallel": true,
"self": 22.73642719901227
},
"communicator.exchange": {
"total": 1087.779973403031,
"count": 63880,
"is_parallel": true,
"self": 1087.779973403031
},
"steps_from_proto": {
"total": 91.29758686100945,
"count": 63880,
"is_parallel": true,
"self": 19.308606460909687,
"children": {
"_process_rank_one_or_two_observation": {
"total": 71.98898040009976,
"count": 511040,
"is_parallel": true,
"self": 71.98898040009976
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 605.9866463020544,
"count": 63881,
"self": 2.3828943660555524,
"children": {
"process_trajectory": {
"total": 102.26565303799498,
"count": 63881,
"self": 101.89563635699506,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3700166809999246,
"count": 2,
"self": 0.3700166809999246
}
}
},
"_update_policy": {
"total": 501.33809889800386,
"count": 450,
"self": 320.6970318189965,
"children": {
"TorchPPOOptimizer.update": {
"total": 180.64106707900737,
"count": 22818,
"self": 180.64106707900737
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2460000107239466e-06,
"count": 1,
"self": 1.2460000107239466e-06
},
"TrainerController._save_models": {
"total": 0.14136097600021458,
"count": 1,
"self": 0.0019322200000715384,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13942875600014304,
"count": 1,
"self": 0.13942875600014304
}
}
}
}
}
}
}