AnnaMats's picture
Second Push
1f27e1f
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.44153398275375366,
"min": 0.44153398275375366,
"max": 1.3355467319488525,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 13281.341796875,
"min": 13281.341796875,
"max": 40515.14453125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989934.0,
"min": 29938.0,
"max": 989934.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989934.0,
"min": 29938.0,
"max": 989934.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5360538959503174,
"min": -0.09771484136581421,
"max": 0.5360538959503174,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 147.41482543945312,
"min": -23.744707107543945,
"max": 147.41482543945312,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.045880451798439026,
"min": 0.010581070557236671,
"max": 0.5021049976348877,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 12.617124557495117,
"min": 2.888632297515869,
"max": 118.99888610839844,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06800152817611686,
"min": 0.0626208541326793,
"max": 0.07585402798444363,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.020022922641753,
"min": 0.5309781958911054,
"max": 1.0388171774815704,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016296319718498528,
"min": 0.0003848882069151467,
"max": 0.016296319718498528,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.24444479577747794,
"min": 0.0053884348968120535,
"max": 0.24444479577747794,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.44773751745333e-06,
"min": 7.44773751745333e-06,
"max": 0.0002952335158745429,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011171606276179995,
"min": 0.00011171606276179995,
"max": 0.0033756046747984996,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10248254666666669,
"min": 0.10248254666666669,
"max": 0.19841117142857143,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5372382000000002,
"min": 1.3888782,
"max": 2.4442315,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025800641199999995,
"min": 0.00025800641199999995,
"max": 0.009841276025714286,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0038700961799999992,
"min": 0.0038700961799999992,
"max": 0.11253762985000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.011442345567047596,
"min": 0.011442345567047596,
"max": 0.5378549695014954,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.17163518071174622,
"min": 0.1698571741580963,
"max": 3.764984607696533,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 346.6024096385542,
"min": 331.79545454545456,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28768.0,
"min": 16737.0,
"max": 33458.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.60518793223134,
"min": -0.9999226326903989,
"max": 1.60518793223134,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 133.23059837520123,
"min": -30.997601613402367,
"max": 140.7999990209937,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.60518793223134,
"min": -0.9999226326903989,
"max": 1.60518793223134,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 133.23059837520123,
"min": -30.997601613402367,
"max": 140.7999990209937,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04125872459115337,
"min": 0.04125872459115337,
"max": 10.914842418011498,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.42447414106573,
"min": 3.42447414106573,
"max": 185.55232110619545,
"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": "1692805951",
"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",
"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": "1692808327"
},
"total": 2375.802249766,
"count": 1,
"self": 0.5414836889999606,
"children": {
"run_training.setup": {
"total": 0.08603750300000002,
"count": 1,
"self": 0.08603750300000002
},
"TrainerController.start_learning": {
"total": 2375.174728574,
"count": 1,
"self": 1.6104274699587222,
"children": {
"TrainerController._reset_env": {
"total": 6.435223317000009,
"count": 1,
"self": 6.435223317000009
},
"TrainerController.advance": {
"total": 2367.0318223880404,
"count": 63669,
"self": 1.6474626610411178,
"children": {
"env_step": {
"total": 1656.2595894459862,
"count": 63669,
"self": 1529.6149483669933,
"children": {
"SubprocessEnvManager._take_step": {
"total": 125.62256894601364,
"count": 63669,
"self": 5.285052924938384,
"children": {
"TorchPolicy.evaluate": {
"total": 120.33751602107526,
"count": 62568,
"self": 120.33751602107526
}
}
},
"workers": {
"total": 1.02207213297919,
"count": 63669,
"self": 0.0,
"children": {
"worker_root": {
"total": 2369.5006298850412,
"count": 63669,
"is_parallel": true,
"self": 970.9220600870476,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006806372999960786,
"count": 1,
"is_parallel": true,
"self": 0.004339678999883745,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002466694000077041,
"count": 8,
"is_parallel": true,
"self": 0.002466694000077041
}
}
},
"UnityEnvironment.step": {
"total": 0.05508127199999535,
"count": 1,
"is_parallel": true,
"self": 0.0006543889999761632,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005038240000203587,
"count": 1,
"is_parallel": true,
"self": 0.0005038240000203587
},
"communicator.exchange": {
"total": 0.05190107900000385,
"count": 1,
"is_parallel": true,
"self": 0.05190107900000385
},
"steps_from_proto": {
"total": 0.002021979999994983,
"count": 1,
"is_parallel": true,
"self": 0.0003985949999218974,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016233850000730854,
"count": 8,
"is_parallel": true,
"self": 0.0016233850000730854
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1398.5785697979936,
"count": 63668,
"is_parallel": true,
"self": 38.27181555097968,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.648736908995204,
"count": 63668,
"is_parallel": true,
"self": 24.648736908995204
},
"communicator.exchange": {
"total": 1218.9988498530163,
"count": 63668,
"is_parallel": true,
"self": 1218.9988498530163
},
"steps_from_proto": {
"total": 116.65916748500229,
"count": 63668,
"is_parallel": true,
"self": 23.363543891041104,
"children": {
"_process_rank_one_or_two_observation": {
"total": 93.29562359396118,
"count": 509344,
"is_parallel": true,
"self": 93.29562359396118
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 709.1247702810131,
"count": 63669,
"self": 3.075229964958453,
"children": {
"process_trajectory": {
"total": 118.341159932057,
"count": 63669,
"self": 118.128314521057,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21284541099998933,
"count": 2,
"self": 0.21284541099998933
}
}
},
"_update_policy": {
"total": 587.7083803839976,
"count": 450,
"self": 383.09043097799736,
"children": {
"TorchPPOOptimizer.update": {
"total": 204.6179494060002,
"count": 22770,
"self": 204.6179494060002
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.660002433520276e-07,
"count": 1,
"self": 9.660002433520276e-07
},
"TrainerController._save_models": {
"total": 0.09725443300021652,
"count": 1,
"self": 0.001454587000353058,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09579984599986346,
"count": 1,
"self": 0.09579984599986346
}
}
}
}
}
}
}