ppo-Pyramids / run_logs /timers.json
jichuanh's picture
First Push
f7cd773 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.18455518782138824,
"min": 0.1723124235868454,
"max": 1.4637889862060547,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 5586.8544921875,
"min": 5155.587890625,
"max": 44405.50390625,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999992.0,
"min": 29952.0,
"max": 2999992.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999992.0,
"min": 29952.0,
"max": 2999992.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7142572402954102,
"min": -0.19251509010791779,
"max": 0.7864418625831604,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 213.5629119873047,
"min": -45.626075744628906,
"max": 230.42745971679688,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.007587899453938007,
"min": -0.022064711898565292,
"max": 0.29288187623023987,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.268781900405884,
"min": -5.935407638549805,
"max": 70.87741088867188,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06870236093511332,
"min": 0.06492414296302568,
"max": 0.07379775105662355,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9618330530915866,
"min": 0.5161230830956068,
"max": 1.100909610608748,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.0156872090212616,
"min": 0.0003961381215027364,
"max": 0.016854510903829664,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2196209262976624,
"min": 0.005545933701038309,
"max": 0.24974252536291408,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.5847851860571435e-06,
"min": 1.5847851860571435e-06,
"max": 0.00029838354339596195,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.2186992604800008e-05,
"min": 2.2186992604800008e-05,
"max": 0.0038435695188101995,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10052822857142858,
"min": 0.10052822857142858,
"max": 0.19946118095238097,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4073952,
"min": 1.3962282666666668,
"max": 2.7225395333333333,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 6.27700342857143e-05,
"min": 6.27700342857143e-05,
"max": 0.009946171977142856,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0008787804800000003,
"min": 0.0008787804800000003,
"max": 0.12813086102000001,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.006940221879631281,
"min": 0.006549749057739973,
"max": 0.48526662588119507,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.09716310352087021,
"min": 0.09169648587703705,
"max": 3.3968663215637207,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 234.1875,
"min": 229.37007874015748,
"max": 999.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29976.0,
"min": 15984.0,
"max": 33084.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7658124904846773,
"min": -1.0000000521540642,
"max": 1.7658124904846773,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 226.0239987820387,
"min": -31.998401671648026,
"max": 226.0239987820387,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7658124904846773,
"min": -1.0000000521540642,
"max": 1.7658124904846773,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 226.0239987820387,
"min": -31.998401671648026,
"max": 226.0239987820387,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.017038425120290412,
"min": 0.016417352189890825,
"max": 9.023397007025778,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.180918415397173,
"min": 1.9111183179775253,
"max": 144.37435211241245,
"count": 100
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1743658307",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/jichuanh/miniconda3/envs/rl-3.10.12/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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1743664658"
},
"total": 6351.261859285063,
"count": 1,
"self": 0.32121283293236047,
"children": {
"run_training.setup": {
"total": 0.02177169208880514,
"count": 1,
"self": 0.02177169208880514
},
"TrainerController.start_learning": {
"total": 6350.918874760042,
"count": 1,
"self": 3.5374433528631926,
"children": {
"TrainerController._reset_env": {
"total": 1.6831322179641575,
"count": 1,
"self": 1.6831322179641575
},
"TrainerController.advance": {
"total": 6345.613099310198,
"count": 194177,
"self": 3.1432087251450866,
"children": {
"env_step": {
"total": 4450.582966240705,
"count": 194177,
"self": 4099.023449446424,
"children": {
"SubprocessEnvManager._take_step": {
"total": 349.4796111759497,
"count": 194177,
"self": 10.215328793041408,
"children": {
"TorchPolicy.evaluate": {
"total": 339.2642823829083,
"count": 187559,
"self": 339.2642823829083
}
}
},
"workers": {
"total": 2.079905618331395,
"count": 194177,
"self": 0.0,
"children": {
"worker_root": {
"total": 6342.9303860571235,
"count": 194177,
"is_parallel": true,
"self": 2558.890832758858,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012643409427255392,
"count": 1,
"is_parallel": true,
"self": 0.00037214194890111685,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008921989938244224,
"count": 8,
"is_parallel": true,
"self": 0.0008921989938244224
}
}
},
"UnityEnvironment.step": {
"total": 0.05491540802177042,
"count": 1,
"is_parallel": true,
"self": 0.0006107420194894075,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005876090144738555,
"count": 1,
"is_parallel": true,
"self": 0.0005876090144738555
},
"communicator.exchange": {
"total": 0.051999189890921116,
"count": 1,
"is_parallel": true,
"self": 0.051999189890921116
},
"steps_from_proto": {
"total": 0.0017178670968860388,
"count": 1,
"is_parallel": true,
"self": 0.0003785090520977974,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013393580447882414,
"count": 8,
"is_parallel": true,
"self": 0.0013393580447882414
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 3784.0395532982657,
"count": 194176,
"is_parallel": true,
"self": 110.62808475561906,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 75.90329294558614,
"count": 194176,
"is_parallel": true,
"self": 75.90329294558614
},
"communicator.exchange": {
"total": 3279.898296020343,
"count": 194176,
"is_parallel": true,
"self": 3279.898296020343
},
"steps_from_proto": {
"total": 317.6098795767175,
"count": 194176,
"is_parallel": true,
"self": 67.21519750030711,
"children": {
"_process_rank_one_or_two_observation": {
"total": 250.3946820764104,
"count": 1553408,
"is_parallel": true,
"self": 250.3946820764104
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1891.8869243443478,
"count": 194177,
"self": 7.538049260387197,
"children": {
"process_trajectory": {
"total": 314.02709195623174,
"count": 194177,
"self": 313.491454832023,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5356371242087334,
"count": 6,
"self": 0.5356371242087334
}
}
},
"_update_policy": {
"total": 1570.3217831277288,
"count": 1394,
"self": 775.8074594498612,
"children": {
"TorchPPOOptimizer.update": {
"total": 794.5143236778677,
"count": 68307,
"self": 794.5143236778677
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.939517334103584e-07,
"count": 1,
"self": 6.939517334103584e-07
},
"TrainerController._save_models": {
"total": 0.0851991850649938,
"count": 1,
"self": 0.000828032149001956,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08437115291599184,
"count": 1,
"self": 0.08437115291599184
}
}
}
}
}
}
}