ppo-PyramidsRND / run_logs /timers.json
eLarry's picture
1st model. Trained on Colab
9607fdf
raw
history blame
19.2 kB
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.38032662868499756,
"min": 0.38032662868499756,
"max": 1.5038046836853027,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 11494.9921875,
"min": 11494.9921875,
"max": 45619.41796875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989880.0,
"min": 29982.0,
"max": 989880.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989880.0,
"min": 29982.0,
"max": 989880.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5438935160636902,
"min": -0.09685348719358444,
"max": 0.5611331462860107,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 149.02682495117188,
"min": -23.341690063476562,
"max": 153.18934631347656,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.009694913402199745,
"min": 0.004379634745419025,
"max": 0.7957695126533508,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.6564061641693115,
"min": 1.1956403255462646,
"max": 189.3931427001953,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06723449872350139,
"min": 0.06603271295328836,
"max": 0.07321319881442505,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0085174808525208,
"min": 0.5713169093450516,
"max": 1.0647161996391783,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014165804126802862,
"min": 0.00017996417233286913,
"max": 0.01992232958021085,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.21248706190204295,
"min": 0.0019796058956615603,
"max": 0.21248706190204295,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 2.504549749546e-05,
"min": 2.504549749546e-05,
"max": 0.0009825421267457874,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0003756824624319,
"min": 0.0003756824624319,
"max": 0.0121154531884547,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10250453999999999,
"min": 0.10250453999999999,
"max": 0.1982542125,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5375680999999999,
"min": 1.4778282,
"max": 2.6115453000000004,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002602035460000001,
"min": 0.0002602035460000001,
"max": 0.009825595828749999,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0039030531900000015,
"min": 0.0039030531900000015,
"max": 0.12117337547,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.00893393438309431,
"min": 0.00893393438309431,
"max": 0.6524242758750916,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.13400901854038239,
"min": 0.12638705968856812,
"max": 5.219394207000732,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 360.6547619047619,
"min": 337.15909090909093,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30295.0,
"min": 17548.0,
"max": 33080.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5440928384306885,
"min": -0.9999290844125133,
"max": 1.5946431645954198,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 129.70379842817783,
"min": -30.99780161678791,
"max": 140.32859848439693,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5440928384306885,
"min": -0.9999290844125133,
"max": 1.5946431645954198,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 129.70379842817783,
"min": -30.99780161678791,
"max": 140.32859848439693,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03321996587190023,
"min": 0.03284552932712937,
"max": 14.21031453129318,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.7904771332396194,
"min": 2.7904771332396194,
"max": 255.78566156327724,
"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": "1678227579",
"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": "1.22.4",
"end_time_seconds": "1678230031"
},
"total": 2452.0135581860004,
"count": 1,
"self": 0.8560289920001196,
"children": {
"run_training.setup": {
"total": 0.11492330800001582,
"count": 1,
"self": 0.11492330800001582
},
"TrainerController.start_learning": {
"total": 2451.0426058860003,
"count": 1,
"self": 1.6305247240393328,
"children": {
"TrainerController._reset_env": {
"total": 6.407814672999848,
"count": 1,
"self": 6.407814672999848
},
"TrainerController.advance": {
"total": 2442.8562074689603,
"count": 63763,
"self": 1.87518065899485,
"children": {
"env_step": {
"total": 1653.6145391020361,
"count": 63763,
"self": 1523.2788634590427,
"children": {
"SubprocessEnvManager._take_step": {
"total": 129.3060507639882,
"count": 63763,
"self": 5.206917850953914,
"children": {
"TorchPolicy.evaluate": {
"total": 124.09913291303428,
"count": 62558,
"self": 42.34526478293492,
"children": {
"TorchPolicy.sample_actions": {
"total": 81.75386813009936,
"count": 62558,
"self": 81.75386813009936
}
}
}
}
},
"workers": {
"total": 1.0296248790052687,
"count": 63763,
"self": 0.0,
"children": {
"worker_root": {
"total": 2444.930228920985,
"count": 63763,
"is_parallel": true,
"self": 1055.3419760291288,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002684187000113525,
"count": 1,
"is_parallel": true,
"self": 0.000901264000503943,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001782922999609582,
"count": 8,
"is_parallel": true,
"self": 0.001782922999609582
}
}
},
"UnityEnvironment.step": {
"total": 0.07833084899993992,
"count": 1,
"is_parallel": true,
"self": 0.0005100260000290291,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004912819999844942,
"count": 1,
"is_parallel": true,
"self": 0.0004912819999844942
},
"communicator.exchange": {
"total": 0.07581059299991466,
"count": 1,
"is_parallel": true,
"self": 0.07581059299991466
},
"steps_from_proto": {
"total": 0.0015189480000117328,
"count": 1,
"is_parallel": true,
"self": 0.00038635699979749916,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011325910002142336,
"count": 8,
"is_parallel": true,
"self": 0.0011325910002142336
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1389.5882528918562,
"count": 63762,
"is_parallel": true,
"self": 34.09456357683666,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.91258705401924,
"count": 63762,
"is_parallel": true,
"self": 24.91258705401924
},
"communicator.exchange": {
"total": 1229.2428866599857,
"count": 63762,
"is_parallel": true,
"self": 1229.2428866599857
},
"steps_from_proto": {
"total": 101.33821560101455,
"count": 63762,
"is_parallel": true,
"self": 24.968863540899747,
"children": {
"_process_rank_one_or_two_observation": {
"total": 76.3693520601148,
"count": 510096,
"is_parallel": true,
"self": 76.3693520601148
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 787.3664877079293,
"count": 63763,
"self": 3.2732395429809458,
"children": {
"process_trajectory": {
"total": 175.06971383695236,
"count": 63763,
"self": 174.829818510952,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2398953260003509,
"count": 2,
"self": 0.2398953260003509
}
}
},
"_update_policy": {
"total": 609.023534327996,
"count": 456,
"self": 236.33637865499645,
"children": {
"TorchPPOOptimizer.update": {
"total": 372.68715567299955,
"count": 22761,
"self": 372.68715567299955
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3190001482143998e-06,
"count": 1,
"self": 1.3190001482143998e-06
},
"TrainerController._save_models": {
"total": 0.14805770100065274,
"count": 1,
"self": 0.0019117380006719031,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14614596299998084,
"count": 1,
"self": 0.14614596299998084
}
}
}
}
}
}
}