ppo-PyramidsRND / run_logs /timers.json
cmenasse's picture
First Push
b13953f
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4531732201576233,
"min": 0.4531732201576233,
"max": 1.3734130859375,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 13653.203125,
"min": 13653.203125,
"max": 41663.859375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989989.0,
"min": 29952.0,
"max": 989989.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989989.0,
"min": 29952.0,
"max": 989989.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.36684155464172363,
"min": -0.10153128951787949,
"max": 0.40479281544685364,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 96.47933197021484,
"min": -24.469039916992188,
"max": 107.67488861083984,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.3203153908252716,
"min": -0.3203153908252716,
"max": 0.4508618414402008,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -84.24295043945312,
"min": -84.24295043945312,
"max": 106.85425567626953,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06555852533525063,
"min": 0.06552008283725244,
"max": 0.0755070433534323,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9833778800287594,
"min": 0.48592991544129116,
"max": 1.0755452341788139,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.029636667554991114,
"min": 0.0002713775291926775,
"max": 0.029636667554991114,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.4445500133248667,
"min": 0.0032565303503121305,
"max": 0.4445500133248667,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.491437502886666e-06,
"min": 7.491437502886666e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001123715625433,
"min": 0.0001123715625433,
"max": 0.0035073422308860005,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10249711333333332,
"min": 0.10249711333333332,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5374567,
"min": 1.3886848,
"max": 2.569114,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025946162199999996,
"min": 0.00025946162199999996,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0038919243299999997,
"min": 0.0038919243299999997,
"max": 0.11693448859999998,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.012985426001250744,
"min": 0.012985426001250744,
"max": 0.5170117616653442,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.19478139281272888,
"min": 0.19360066950321198,
"max": 3.61908221244812,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 468.6470588235294,
"min": 396.3142857142857,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31868.0,
"min": 15984.0,
"max": 32967.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.2325671424171818,
"min": -1.0000000521540642,
"max": 1.446695361343714,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 82.58199854195118,
"min": -31.99480165541172,
"max": 100.25439849495888,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.2325671424171818,
"min": -1.0000000521540642,
"max": 1.446695361343714,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 82.58199854195118,
"min": -31.99480165541172,
"max": 100.25439849495888,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.06356952060187764,
"min": 0.057379606847410156,
"max": 10.74631842970848,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.259157880325802,
"min": 4.016572479318711,
"max": 171.9410948753357,
"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": "1674245379",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1674247408"
},
"total": 2029.2822518830003,
"count": 1,
"self": 0.4243440029999874,
"children": {
"run_training.setup": {
"total": 0.10125809900000604,
"count": 1,
"self": 0.10125809900000604
},
"TrainerController.start_learning": {
"total": 2028.7566497810003,
"count": 1,
"self": 1.466530409106781,
"children": {
"TrainerController._reset_env": {
"total": 6.114088193000043,
"count": 1,
"self": 6.114088193000043
},
"TrainerController.advance": {
"total": 2021.0890917048923,
"count": 63438,
"self": 1.43814088493491,
"children": {
"env_step": {
"total": 1372.5757362409472,
"count": 63438,
"self": 1260.1229253040556,
"children": {
"SubprocessEnvManager._take_step": {
"total": 111.57760769992865,
"count": 63438,
"self": 4.470603252860656,
"children": {
"TorchPolicy.evaluate": {
"total": 107.107004447068,
"count": 62549,
"self": 35.1057260929806,
"children": {
"TorchPolicy.sample_actions": {
"total": 72.00127835408739,
"count": 62549,
"self": 72.00127835408739
}
}
}
}
},
"workers": {
"total": 0.8752032369629887,
"count": 63438,
"self": 0.0,
"children": {
"worker_root": {
"total": 2023.8370147460873,
"count": 63438,
"is_parallel": true,
"self": 868.9375492449531,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018652700000529876,
"count": 1,
"is_parallel": true,
"self": 0.0007236319997900864,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011416380002629012,
"count": 8,
"is_parallel": true,
"self": 0.0011416380002629012
}
}
},
"UnityEnvironment.step": {
"total": 0.0495873169998049,
"count": 1,
"is_parallel": true,
"self": 0.000501051999435731,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004875640001955617,
"count": 1,
"is_parallel": true,
"self": 0.0004875640001955617
},
"communicator.exchange": {
"total": 0.046953080000093905,
"count": 1,
"is_parallel": true,
"self": 0.046953080000093905
},
"steps_from_proto": {
"total": 0.0016456210000797,
"count": 1,
"is_parallel": true,
"self": 0.0004149379997215874,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012306830003581126,
"count": 8,
"is_parallel": true,
"self": 0.0012306830003581126
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1154.8994655011343,
"count": 63437,
"is_parallel": true,
"self": 28.062510003941497,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 21.805948003049707,
"count": 63437,
"is_parallel": true,
"self": 21.805948003049707
},
"communicator.exchange": {
"total": 1005.7023900210406,
"count": 63437,
"is_parallel": true,
"self": 1005.7023900210406
},
"steps_from_proto": {
"total": 99.32861747310244,
"count": 63437,
"is_parallel": true,
"self": 22.50431581013754,
"children": {
"_process_rank_one_or_two_observation": {
"total": 76.8243016629649,
"count": 507496,
"is_parallel": true,
"self": 76.8243016629649
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 647.0752145790102,
"count": 63438,
"self": 2.7391356780681235,
"children": {
"process_trajectory": {
"total": 141.42082885493937,
"count": 63438,
"self": 141.2407104029403,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1801184519990784,
"count": 2,
"self": 0.1801184519990784
}
}
},
"_update_policy": {
"total": 502.9152500460027,
"count": 449,
"self": 190.57786242191924,
"children": {
"TorchPPOOptimizer.update": {
"total": 312.3373876240835,
"count": 22800,
"self": 312.3373876240835
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.10000380827114e-07,
"count": 1,
"self": 9.10000380827114e-07
},
"TrainerController._save_models": {
"total": 0.08693856400077493,
"count": 1,
"self": 0.0015216360006888863,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08541692800008605,
"count": 1,
"self": 0.08541692800008605
}
}
}
}
}
}
}