ppo-Pyramids / run_logs /timers.json
omerozerr's picture
First Push
05a7fc3 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.998950719833374,
"min": 0.9001078605651855,
"max": 1.4380332231521606,
"count": 13
},
"Pyramids.Policy.Entropy.sum": {
"value": 30256.21875,
"min": 26960.03125,
"max": 43624.17578125,
"count": 13
},
"Pyramids.Step.mean": {
"value": 389922.0,
"min": 29952.0,
"max": 389922.0,
"count": 13
},
"Pyramids.Step.sum": {
"value": 389922.0,
"min": 29952.0,
"max": 389922.0,
"count": 13
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.04003271833062172,
"min": -0.270123153924942,
"max": 0.04003271833062172,
"count": 13
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 9.968147277832031,
"min": -64.0191879272461,
"max": 9.968147277832031,
"count": 13
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.03113975003361702,
"min": 0.03113975003361702,
"max": 0.33837276697158813,
"count": 13
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 7.75379753112793,
"min": 7.75379753112793,
"max": 81.20946502685547,
"count": 13
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07138317823434492,
"min": 0.06532376273643901,
"max": 0.07496527767407479,
"count": 13
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9993644952808289,
"min": 0.5247569437185235,
"max": 0.9993978770180985,
"count": 13
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.005047186439996159,
"min": 0.0006489568515479398,
"max": 0.00795678350329263,
"count": 13
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.07066061015994622,
"min": 0.009085395921671157,
"max": 0.07066061015994622,
"count": 13
},
"Pyramids.Policy.LearningRate.mean": {
"value": 0.00018756205176504283,
"min": 0.00018756205176504283,
"max": 0.00029515063018788575,
"count": 13
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0026258687247105996,
"min": 0.0020660544113152,
"max": 0.0035081708306098002,
"count": 13
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.16252067142857143,
"min": 0.16252067142857143,
"max": 0.19838354285714285,
"count": 13
},
"Pyramids.Policy.Epsilon.sum": {
"value": 2.2752894,
"min": 1.3886848,
"max": 2.5693902,
"count": 13
},
"Pyramids.Policy.Beta.mean": {
"value": 0.006255815075714286,
"min": 0.006255815075714286,
"max": 0.00983851593142857,
"count": 13
},
"Pyramids.Policy.Beta.sum": {
"value": 0.08758141106,
"min": 0.06886961152,
"max": 0.11696208098000001,
"count": 13
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.026629071682691574,
"min": 0.026629071682691574,
"max": 0.5501084923744202,
"count": 13
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.37280699610710144,
"min": 0.37280699610710144,
"max": 3.850759267807007,
"count": 13
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 817.1891891891892,
"min": 817.1891891891892,
"max": 999.0,
"count": 13
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30236.0,
"min": 15984.0,
"max": 32383.0,
"count": 13
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.1554540216520026,
"min": -1.0000000521540642,
"max": 0.1554540216520026,
"count": 13
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 5.751798801124096,
"min": -30.374401703476906,
"max": 5.751798801124096,
"count": 13
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.1554540216520026,
"min": -1.0000000521540642,
"max": 0.1554540216520026,
"count": 13
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 5.751798801124096,
"min": -30.374401703476906,
"max": 5.751798801124096,
"count": 13
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.2267604800841041,
"min": 0.2267604800841041,
"max": 11.075799133628607,
"count": 13
},
"Pyramids.Policy.RndReward.sum": {
"value": 8.390137763111852,
"min": 8.390137763111852,
"max": 177.2127861380577,
"count": 13
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 13
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 13
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1739707764",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.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": "1739708387"
},
"total": 623.555400056,
"count": 1,
"self": 0.207407645000103,
"children": {
"run_training.setup": {
"total": 0.0207760230000531,
"count": 1,
"self": 0.0207760230000531
},
"TrainerController.start_learning": {
"total": 623.3272163879999,
"count": 1,
"self": 0.5804582989712799,
"children": {
"TrainerController._reset_env": {
"total": 2.128190472999904,
"count": 1,
"self": 2.128190472999904
},
"TrainerController.advance": {
"total": 620.6185676160287,
"count": 24668,
"self": 0.35215339301498716,
"children": {
"env_step": {
"total": 381.4078416239993,
"count": 24668,
"self": 326.8474191459836,
"children": {
"SubprocessEnvManager._take_step": {
"total": 54.282723165007155,
"count": 24668,
"self": 1.6065761640165874,
"children": {
"TorchPolicy.evaluate": {
"total": 52.67614700099057,
"count": 24493,
"self": 52.67614700099057
}
}
},
"workers": {
"total": 0.2776993130084975,
"count": 24668,
"self": 0.0,
"children": {
"worker_root": {
"total": 621.8310794920035,
"count": 24668,
"is_parallel": true,
"self": 328.1429784449724,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020393869999679737,
"count": 1,
"is_parallel": true,
"self": 0.0007243360000757093,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013150509998922644,
"count": 8,
"is_parallel": true,
"self": 0.0013150509998922644
}
}
},
"UnityEnvironment.step": {
"total": 0.03658156300002702,
"count": 1,
"is_parallel": true,
"self": 0.00034424299997226626,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00032593700007055304,
"count": 1,
"is_parallel": true,
"self": 0.00032593700007055304
},
"communicator.exchange": {
"total": 0.03484145399988847,
"count": 1,
"is_parallel": true,
"self": 0.03484145399988847
},
"steps_from_proto": {
"total": 0.0010699290000957262,
"count": 1,
"is_parallel": true,
"self": 0.000244267999960357,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008256610001353692,
"count": 8,
"is_parallel": true,
"self": 0.0008256610001353692
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 293.68810104703107,
"count": 24667,
"is_parallel": true,
"self": 7.555183527048712,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.121828956032232,
"count": 24667,
"is_parallel": true,
"self": 5.121828956032232
},
"communicator.exchange": {
"total": 258.0160779459791,
"count": 24667,
"is_parallel": true,
"self": 258.0160779459791
},
"steps_from_proto": {
"total": 22.995010617971047,
"count": 24667,
"is_parallel": true,
"self": 4.918657078003889,
"children": {
"_process_rank_one_or_two_observation": {
"total": 18.076353539967158,
"count": 197336,
"is_parallel": true,
"self": 18.076353539967158
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 238.7443043300143,
"count": 24668,
"self": 1.4473783860100866,
"children": {
"process_trajectory": {
"total": 42.442379013004484,
"count": 24668,
"self": 42.442379013004484
},
"_update_policy": {
"total": 194.85454693099973,
"count": 163,
"self": 107.04484613799445,
"children": {
"TorchPPOOptimizer.update": {
"total": 87.80970079300528,
"count": 8920,
"self": 87.80970079300528
}
}
}
}
},
"trainer_threads": {
"total": 1.3240000953373965e-06,
"count": 1,
"self": 1.3240000953373965e-06
},
"TrainerController._save_models": {
"total": 0.11426694500005397,
"count": 1,
"self": 0.0014725500000167813,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11279439500003718,
"count": 1,
"self": 0.11279439500003718
}
}
}
}
}
}
}
}
}