ppo-Pyramids / run_logs /timers.json
vxst2's picture
Init commit
91e1e3c verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.2401433289051056,
"min": 0.21638180315494537,
"max": 1.5460220575332642,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 7277.30322265625,
"min": 6487.9921875,
"max": 46900.125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989962.0,
"min": 29952.0,
"max": 989962.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989962.0,
"min": 29952.0,
"max": 989962.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.3226073384284973,
"min": -0.09783951193094254,
"max": 0.45063143968582153,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 85.1683349609375,
"min": -23.481483459472656,
"max": 120.76922607421875,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.032659921795129776,
"min": -0.032659921795129776,
"max": 0.49173504114151,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -8.62221908569336,
"min": -8.62221908569336,
"max": 118.50814819335938,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.031482500600672904,
"min": 0.028814184875781874,
"max": 0.036640466218933646,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.44075500840942067,
"min": 0.24928468562263464,
"max": 0.5099203964928165,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.011487822356035135,
"min": 0.00040087653696034635,
"max": 0.15304372761404292,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.16082951298449188,
"min": 0.0056122715174448485,
"max": 1.0713060932983005,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.301066899488571e-05,
"min": 7.301066899488571e-05,
"max": 0.002951506287330743,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0010221493659284,
"min": 0.0010221493659284,
"max": 0.03633041418898621,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10243368571428571,
"min": 0.10243368571428571,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4340716,
"min": 1.3886848,
"max": 2.6110138000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002531252028571429,
"min": 0.0002531252028571429,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003543752840000001,
"min": 0.003543752840000001,
"max": 0.12112027861999998,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.0159149169921875,
"min": 0.0159149169921875,
"max": 0.5423343181610107,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.222808837890625,
"min": 0.222808837890625,
"max": 4.338674545288086,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 450.71014492753625,
"min": 363.39473684210526,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31099.0,
"min": 15984.0,
"max": 33400.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.1031764404957785,
"min": -1.0000000521540642,
"max": 1.557631560650311,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 75.01599795371294,
"min": -29.432001680135727,
"max": 118.37999860942364,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.1031764404957785,
"min": -1.0000000521540642,
"max": 1.557631560650311,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 75.01599795371294,
"min": -29.432001680135727,
"max": 118.37999860942364,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.07515835665125291,
"min": 0.07515835665125291,
"max": 6.418743187561631,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 5.110768252285197,
"min": 5.018989227944985,
"max": 202.6122723221779,
"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": "1718820095",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1718821485"
},
"total": 1389.9789536289998,
"count": 1,
"self": 0.32239306299993586,
"children": {
"run_training.setup": {
"total": 0.05327401199997439,
"count": 1,
"self": 0.05327401199997439
},
"TrainerController.start_learning": {
"total": 1389.6032865539999,
"count": 1,
"self": 1.173453908979127,
"children": {
"TrainerController._reset_env": {
"total": 2.2067193469999893,
"count": 1,
"self": 2.2067193469999893
},
"TrainerController.advance": {
"total": 1386.1439400450206,
"count": 63585,
"self": 1.1662080310129568,
"children": {
"env_step": {
"total": 1007.3406855739722,
"count": 63585,
"self": 892.1560281789575,
"children": {
"SubprocessEnvManager._take_step": {
"total": 114.4585991650165,
"count": 63585,
"self": 4.154571814008023,
"children": {
"TorchPolicy.evaluate": {
"total": 110.30402735100847,
"count": 62557,
"self": 110.30402735100847
}
}
},
"workers": {
"total": 0.7260582299982161,
"count": 63585,
"self": 0.0,
"children": {
"worker_root": {
"total": 1387.6717797539904,
"count": 63585,
"is_parallel": true,
"self": 588.8702891340001,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002013459999943734,
"count": 1,
"is_parallel": true,
"self": 0.0006374140000389161,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001376045999904818,
"count": 8,
"is_parallel": true,
"self": 0.001376045999904818
}
}
},
"UnityEnvironment.step": {
"total": 0.03505291600004057,
"count": 1,
"is_parallel": true,
"self": 0.0004545939998479298,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003040510000573704,
"count": 1,
"is_parallel": true,
"self": 0.0003040510000573704
},
"communicator.exchange": {
"total": 0.033198711000068215,
"count": 1,
"is_parallel": true,
"self": 0.033198711000068215
},
"steps_from_proto": {
"total": 0.001095560000067053,
"count": 1,
"is_parallel": true,
"self": 0.0002502220002043032,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008453379998627497,
"count": 8,
"is_parallel": true,
"self": 0.0008453379998627497
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 798.8014906199903,
"count": 63584,
"is_parallel": true,
"self": 21.15786442405488,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 13.835364045955657,
"count": 63584,
"is_parallel": true,
"self": 13.835364045955657
},
"communicator.exchange": {
"total": 703.4096773949891,
"count": 63584,
"is_parallel": true,
"self": 703.4096773949891
},
"steps_from_proto": {
"total": 60.39858475499068,
"count": 63584,
"is_parallel": true,
"self": 12.96776691113314,
"children": {
"_process_rank_one_or_two_observation": {
"total": 47.43081784385754,
"count": 508672,
"is_parallel": true,
"self": 47.43081784385754
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 377.6370464400354,
"count": 63585,
"self": 2.1941723190248013,
"children": {
"process_trajectory": {
"total": 109.37143476200708,
"count": 63585,
"self": 109.18682741400698,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1846073480000996,
"count": 2,
"self": 0.1846073480000996
}
}
},
"_update_policy": {
"total": 266.07143935900353,
"count": 448,
"self": 207.19762705199219,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.87381230701135,
"count": 5613,
"self": 58.87381230701135
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0660000953066628e-06,
"count": 1,
"self": 1.0660000953066628e-06
},
"TrainerController._save_models": {
"total": 0.07917218700004014,
"count": 1,
"self": 0.001318103999892628,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07785408300014751,
"count": 1,
"self": 0.07785408300014751
}
}
}
}
}
}
}