Deinigu's picture
First Training
fc2d5af verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.6688451766967773,
"min": 0.6688451766967773,
"max": 1.379045009613037,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 20118.86328125,
"min": 20118.86328125,
"max": 41834.7109375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989983.0,
"min": 29952.0,
"max": 989983.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989983.0,
"min": 29952.0,
"max": 989983.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.26715341210365295,
"min": -0.09533191472291946,
"max": 0.2759658694267273,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 68.92558288574219,
"min": -22.87965965270996,
"max": 71.75112915039062,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.019729115068912506,
"min": 0.003633086569607258,
"max": 0.3206677734851837,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 5.09011173248291,
"min": 0.9228039979934692,
"max": 75.99826049804688,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06900433907738059,
"min": 0.0661814542725638,
"max": 0.0743202716915957,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0350650861607087,
"min": 0.47125763991605435,
"max": 1.0716222316419304,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014148100695988998,
"min": 0.0004459293418122344,
"max": 0.014148100695988998,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21222151043983498,
"min": 0.004905222759934579,
"max": 0.21222151043983498,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.526957491046675e-06,
"min": 7.526957491046675e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00011290436236570012,
"min": 0.00011290436236570012,
"max": 0.0033764308745231003,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10250895333333335,
"min": 0.10250895333333335,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5376343000000001,
"min": 1.3886848,
"max": 2.4432905000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002606444380000003,
"min": 0.0002606444380000003,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003909666570000005,
"min": 0.003909666570000005,
"max": 0.11256514231,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009667969308793545,
"min": 0.00966647919267416,
"max": 0.408654123544693,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1450195461511612,
"min": 0.1353307068347931,
"max": 2.860578775405884,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 530.7166666666667,
"min": 512.5636363636364,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31843.0,
"min": 15984.0,
"max": 32895.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.1708847126465733,
"min": -1.0000000521540642,
"max": 1.1964436135508798,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 69.08219804614782,
"min": -31.99760165810585,
"max": 69.08219804614782,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.1708847126465733,
"min": -1.0000000521540642,
"max": 1.1964436135508798,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 69.08219804614782,
"min": -31.99760165810585,
"max": 69.08219804614782,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.05300678480100834,
"min": 0.05300678480100834,
"max": 7.741878571920097,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.127400303259492,
"min": 2.8250698554038536,
"max": 123.87005715072155,
"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": "1762518732",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1762520967"
},
"total": 2235.2132805599995,
"count": 1,
"self": 0.7303387129995826,
"children": {
"run_training.setup": {
"total": 0.02537448899965966,
"count": 1,
"self": 0.02537448899965966
},
"TrainerController.start_learning": {
"total": 2234.4575673580002,
"count": 1,
"self": 1.6792499979264903,
"children": {
"TrainerController._reset_env": {
"total": 2.0749677060002796,
"count": 1,
"self": 2.0749677060002796
},
"TrainerController.advance": {
"total": 2230.6285353400735,
"count": 63460,
"self": 1.6003186571506376,
"children": {
"env_step": {
"total": 1566.6095009659512,
"count": 63460,
"self": 1399.9619316530125,
"children": {
"SubprocessEnvManager._take_step": {
"total": 165.6703305719493,
"count": 63460,
"self": 4.8346979238658605,
"children": {
"TorchPolicy.evaluate": {
"total": 160.83563264808345,
"count": 62556,
"self": 160.83563264808345
}
}
},
"workers": {
"total": 0.9772387409893781,
"count": 63460,
"self": 0.0,
"children": {
"worker_root": {
"total": 2227.7881951279323,
"count": 63460,
"is_parallel": true,
"self": 953.8908551229733,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0034688890000325046,
"count": 1,
"is_parallel": true,
"self": 0.0006467800003520097,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002822108999680495,
"count": 8,
"is_parallel": true,
"self": 0.002822108999680495
}
}
},
"UnityEnvironment.step": {
"total": 0.05328254200048832,
"count": 1,
"is_parallel": true,
"self": 0.0005258010005491087,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041716299983818317,
"count": 1,
"is_parallel": true,
"self": 0.00041716299983818317
},
"communicator.exchange": {
"total": 0.050549059999866586,
"count": 1,
"is_parallel": true,
"self": 0.050549059999866586
},
"steps_from_proto": {
"total": 0.0017905180002344423,
"count": 1,
"is_parallel": true,
"self": 0.00037556000006588874,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014149580001685536,
"count": 8,
"is_parallel": true,
"self": 0.0014149580001685536
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1273.897340004959,
"count": 63459,
"is_parallel": true,
"self": 34.54572629900031,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.426492284032975,
"count": 63459,
"is_parallel": true,
"self": 23.426492284032975
},
"communicator.exchange": {
"total": 1104.9015785919364,
"count": 63459,
"is_parallel": true,
"self": 1104.9015785919364
},
"steps_from_proto": {
"total": 111.02354282998931,
"count": 63459,
"is_parallel": true,
"self": 23.494672707613972,
"children": {
"_process_rank_one_or_two_observation": {
"total": 87.52887012237534,
"count": 507672,
"is_parallel": true,
"self": 87.52887012237534
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 662.4187157169717,
"count": 63460,
"self": 3.015280860047824,
"children": {
"process_trajectory": {
"total": 125.45472257892743,
"count": 63460,
"self": 125.27681970392769,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1779028749997451,
"count": 2,
"self": 0.1779028749997451
}
}
},
"_update_policy": {
"total": 533.9487122779965,
"count": 448,
"self": 297.26863602400226,
"children": {
"TorchPPOOptimizer.update": {
"total": 236.68007625399423,
"count": 22731,
"self": 236.68007625399423
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0229996405541897e-06,
"count": 1,
"self": 1.0229996405541897e-06
},
"TrainerController._save_models": {
"total": 0.07481329100028233,
"count": 1,
"self": 0.0009948970000550617,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07381839400022727,
"count": 1,
"self": 0.07381839400022727
}
}
}
}
}
}
}