yotoshihiro's picture
Initial commit
b3dfe0b
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.34538930654525757,
"min": 0.336806058883667,
"max": 1.397656798362732,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 10328.521484375,
"min": 10044.904296875,
"max": 42399.31640625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989872.0,
"min": 29952.0,
"max": 989872.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989872.0,
"min": 29952.0,
"max": 989872.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.50215083360672,
"min": -0.10590985417366028,
"max": 0.5667244791984558,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 135.0785675048828,
"min": -25.418365478515625,
"max": 158.1161346435547,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.05798965319991112,
"min": -0.05798965319991112,
"max": 0.340483158826828,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -15.59921646118164,
"min": -15.59921646118164,
"max": 82.05644226074219,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07348335072424055,
"min": 0.06461799899296326,
"max": 0.07348335072424055,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.1022502608636082,
"min": 0.4863333582209729,
"max": 1.1022502608636082,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013888242054640105,
"min": 0.00039530219608324436,
"max": 0.014244890749234466,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2083236308196016,
"min": 0.004743626352998932,
"max": 0.2083236308196016,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.456077514673335e-06,
"min": 7.456077514673335e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011184116272010002,
"min": 0.00011184116272010002,
"max": 0.0035071226309591995,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10248532666666668,
"min": 0.10248532666666668,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5372799000000001,
"min": 1.3886848,
"max": 2.5690408000000002,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002582841340000001,
"min": 0.0002582841340000001,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003874262010000002,
"min": 0.003874262010000002,
"max": 0.11692717592,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009442646987736225,
"min": 0.009353173896670341,
"max": 0.5832369923591614,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.14163970947265625,
"min": 0.13094443082809448,
"max": 4.082658767700195,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 364.7,
"min": 337.8777777777778,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29176.0,
"min": 15984.0,
"max": 33495.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5102674740366637,
"min": -1.0000000521540642,
"max": 1.6154921166180225,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 120.8213979229331,
"min": -31.9992016851902,
"max": 143.778798379004,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5102674740366637,
"min": -1.0000000521540642,
"max": 1.6154921166180225,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 120.8213979229331,
"min": -31.9992016851902,
"max": 143.778798379004,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03580321103590904,
"min": 0.03580321103590904,
"max": 11.787460276857018,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.8642568828727235,
"min": 2.8284887512854766,
"max": 188.5993644297123,
"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": "1684055287",
"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": "1684057663"
},
"total": 2375.4962257320003,
"count": 1,
"self": 0.42474630100059585,
"children": {
"run_training.setup": {
"total": 0.038292009000088,
"count": 1,
"self": 0.038292009000088
},
"TrainerController.start_learning": {
"total": 2375.0331874219996,
"count": 1,
"self": 1.6797759010091795,
"children": {
"TrainerController._reset_env": {
"total": 3.7856193699999494,
"count": 1,
"self": 3.7856193699999494
},
"TrainerController.advance": {
"total": 2369.4737474329904,
"count": 63744,
"self": 1.626459168821384,
"children": {
"env_step": {
"total": 1702.9557070770393,
"count": 63744,
"self": 1577.1239877600506,
"children": {
"SubprocessEnvManager._take_step": {
"total": 124.89200574702363,
"count": 63744,
"self": 5.380236855009571,
"children": {
"TorchPolicy.evaluate": {
"total": 119.51176889201406,
"count": 62556,
"self": 119.51176889201406
}
}
},
"workers": {
"total": 0.9397135699650789,
"count": 63744,
"self": 0.0,
"children": {
"worker_root": {
"total": 2369.0951760290095,
"count": 63744,
"is_parallel": true,
"self": 920.6792616639691,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018596340000840428,
"count": 1,
"is_parallel": true,
"self": 0.0005886980002287601,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012709359998552827,
"count": 8,
"is_parallel": true,
"self": 0.0012709359998552827
}
}
},
"UnityEnvironment.step": {
"total": 0.048933417000171175,
"count": 1,
"is_parallel": true,
"self": 0.0005697099995813915,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005103690000396455,
"count": 1,
"is_parallel": true,
"self": 0.0005103690000396455
},
"communicator.exchange": {
"total": 0.0461078080002153,
"count": 1,
"is_parallel": true,
"self": 0.0461078080002153
},
"steps_from_proto": {
"total": 0.0017455300003348384,
"count": 1,
"is_parallel": true,
"self": 0.0003741140003512555,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013714159999835829,
"count": 8,
"is_parallel": true,
"self": 0.0013714159999835829
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1448.4159143650404,
"count": 63743,
"is_parallel": true,
"self": 33.79867842193971,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 25.26441360097806,
"count": 63743,
"is_parallel": true,
"self": 25.26441360097806
},
"communicator.exchange": {
"total": 1280.5157757220659,
"count": 63743,
"is_parallel": true,
"self": 1280.5157757220659
},
"steps_from_proto": {
"total": 108.83704662005675,
"count": 63743,
"is_parallel": true,
"self": 23.067877299149586,
"children": {
"_process_rank_one_or_two_observation": {
"total": 85.76916932090717,
"count": 509944,
"is_parallel": true,
"self": 85.76916932090717
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 664.8915811871298,
"count": 63744,
"self": 2.997635954126963,
"children": {
"process_trajectory": {
"total": 118.41278466000176,
"count": 63744,
"self": 118.18451573800166,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22826892200009752,
"count": 2,
"self": 0.22826892200009752
}
}
},
"_update_policy": {
"total": 543.481160573001,
"count": 447,
"self": 350.39922177102244,
"children": {
"TorchPPOOptimizer.update": {
"total": 193.0819388019786,
"count": 22815,
"self": 193.0819388019786
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1239999366807751e-06,
"count": 1,
"self": 1.1239999366807751e-06
},
"TrainerController._save_models": {
"total": 0.09404359400014073,
"count": 1,
"self": 0.0013581880002675462,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09268540599987318,
"count": 1,
"self": 0.09268540599987318
}
}
}
}
}
}
}