ppo-Pyramids / run_logs /timers.json
nvasko's picture
First Push
77006c9 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5406646728515625,
"min": 0.5347597002983093,
"max": 1.3720085620880127,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 16479.458984375,
"min": 16017.123046875,
"max": 41621.25,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989992.0,
"min": 29953.0,
"max": 989992.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989992.0,
"min": 29953.0,
"max": 989992.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.3703041970729828,
"min": -0.09217029064893723,
"max": 0.3703041970729828,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 98.87122344970703,
"min": -22.12087059020996,
"max": 98.87122344970703,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.08840557187795639,
"min": -0.08840557187795639,
"max": 0.6114280223846436,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -23.60428810119629,
"min": -23.60428810119629,
"max": 145.51986694335938,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07125641911096396,
"min": 0.06521685808555924,
"max": 0.07227953583727974,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9975898675534955,
"min": 0.6369031765086202,
"max": 1.0841930375591962,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015819961605801854,
"min": 0.00043347969166243204,
"max": 0.015819961605801854,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22147946248122596,
"min": 0.0052017562999491845,
"max": 0.22147946248122596,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.680376011335713e-06,
"min": 7.680376011335713e-06,
"max": 0.00029475483508172224,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010752526415869997,
"min": 0.00010752526415869997,
"max": 0.0035069786310071996,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10256009285714285,
"min": 0.10256009285714285,
"max": 0.19825161111111111,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4358412999999999,
"min": 1.4358412999999999,
"max": 2.5689928,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026575327642857136,
"min": 0.00026575327642857136,
"max": 0.00982533595,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003720545869999999,
"min": 0.003720545869999999,
"max": 0.11692238072000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010320176370441914,
"min": 0.01031129714101553,
"max": 0.566263735294342,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.14448246359825134,
"min": 0.14435815811157227,
"max": 5.096373558044434,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 461.7692307692308,
"min": 461.7692307692308,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30015.0,
"min": 18030.0,
"max": 32648.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.356569675107797,
"min": -0.9999667187531789,
"max": 1.356569675107797,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 89.5335985571146,
"min": -30.678001657128334,
"max": 89.5335985571146,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.356569675107797,
"min": -0.9999667187531789,
"max": 1.356569675107797,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 89.5335985571146,
"min": -30.678001657128334,
"max": 89.5335985571146,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.050071535563884856,
"min": 0.050071535563884856,
"max": 11.134878201704277,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.3047213472164003,
"min": 3.3047213472164003,
"max": 211.56268583238125,
"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": "1713974217",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/nick/anaconda3/envs/unity/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1713974791"
},
"total": 574.6476667859988,
"count": 1,
"self": 0.16688554099891917,
"children": {
"run_training.setup": {
"total": 0.05044033299964212,
"count": 1,
"self": 0.05044033299964212
},
"TrainerController.start_learning": {
"total": 574.4303409120002,
"count": 1,
"self": 0.3846188443603751,
"children": {
"TrainerController._reset_env": {
"total": 0.9010285309996107,
"count": 1,
"self": 0.9010285309996107
},
"TrainerController.advance": {
"total": 573.1081990056409,
"count": 63503,
"self": 0.3819802285215701,
"children": {
"env_step": {
"total": 373.7783504992367,
"count": 63503,
"self": 336.3986238221478,
"children": {
"SubprocessEnvManager._take_step": {
"total": 37.11149746709452,
"count": 63503,
"self": 1.4327241833598237,
"children": {
"TorchPolicy.evaluate": {
"total": 35.6787732837347,
"count": 62563,
"self": 35.6787732837347
}
}
},
"workers": {
"total": 0.26822920999438793,
"count": 63503,
"self": 0.0,
"children": {
"worker_root": {
"total": 573.787696311907,
"count": 63503,
"is_parallel": true,
"self": 268.3320666607542,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0006786350004404085,
"count": 1,
"is_parallel": true,
"self": 0.00018078900029649958,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004978460001439089,
"count": 8,
"is_parallel": true,
"self": 0.0004978460001439089
}
}
},
"UnityEnvironment.step": {
"total": 0.01436201400065329,
"count": 1,
"is_parallel": true,
"self": 0.00012222899931657594,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00015477899978577625,
"count": 1,
"is_parallel": true,
"self": 0.00015477899978577625
},
"communicator.exchange": {
"total": 0.013709849001315888,
"count": 1,
"is_parallel": true,
"self": 0.013709849001315888
},
"steps_from_proto": {
"total": 0.00037515700023504905,
"count": 1,
"is_parallel": true,
"self": 9.243899876310024e-05,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0002827180014719488,
"count": 8,
"is_parallel": true,
"self": 0.0002827180014719488
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 305.4556296511528,
"count": 63502,
"is_parallel": true,
"self": 6.559475191908859,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.705623664181985,
"count": 63502,
"is_parallel": true,
"self": 4.705623664181985
},
"communicator.exchange": {
"total": 275.7986656561334,
"count": 63502,
"is_parallel": true,
"self": 275.7986656561334
},
"steps_from_proto": {
"total": 18.39186513892855,
"count": 63502,
"is_parallel": true,
"self": 3.6994934216436377,
"children": {
"_process_rank_one_or_two_observation": {
"total": 14.692371717284914,
"count": 508016,
"is_parallel": true,
"self": 14.692371717284914
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 198.94786827788266,
"count": 63503,
"self": 0.7587247269584623,
"children": {
"process_trajectory": {
"total": 39.91170769992277,
"count": 63503,
"self": 39.827054145924194,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08465355399857799,
"count": 2,
"self": 0.08465355399857799
}
}
},
"_update_policy": {
"total": 158.27743585100143,
"count": 454,
"self": 93.66818708000756,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.60924877099387,
"count": 22785,
"self": 64.60924877099387
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.4999978854320943e-07,
"count": 1,
"self": 4.4999978854320943e-07
},
"TrainerController._save_models": {
"total": 0.036494080999545986,
"count": 1,
"self": 0.0009922890003508655,
"children": {
"RLTrainer._checkpoint": {
"total": 0.03550179199919512,
"count": 1,
"self": 0.03550179199919512
}
}
}
}
}
}
}