testpyramidsrnd / run_logs /timers.json
Tstarshak's picture
First Pyramids
24896ca
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.41532936692237854,
"min": 0.41532936692237854,
"max": 1.4610974788665771,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12612.72265625,
"min": 12612.72265625,
"max": 44323.8515625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989997.0,
"min": 29952.0,
"max": 989997.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989997.0,
"min": 29952.0,
"max": 989997.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.22085046768188477,
"min": -0.16713948547840118,
"max": 0.22085046768188477,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 56.5377197265625,
"min": -39.612056732177734,
"max": 56.5377197265625,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.07109145820140839,
"min": 0.007225059904158115,
"max": 0.4674621522426605,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 18.199413299560547,
"min": 1.7845897674560547,
"max": 110.78852844238281,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07047669774536709,
"min": 0.06543724591640301,
"max": 0.07401030313519928,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9866737684351392,
"min": 0.4839584918135052,
"max": 1.0641597351150625,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.011617206489007341,
"min": 0.00018257017461247477,
"max": 0.011617206489007341,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.16264089084610278,
"min": 0.0012779912222873233,
"max": 0.16264089084610278,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.612276034035713e-06,
"min": 7.612276034035713e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010657186447649998,
"min": 0.00010657186447649998,
"max": 0.003127518357494,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10253739285714285,
"min": 0.10253739285714285,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4355235,
"min": 1.327104,
"max": 2.442506,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026348554642857143,
"min": 0.00026348554642857143,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00368879765,
"min": 0.00368879765,
"max": 0.10428634939999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.011858736164867878,
"min": 0.011858736164867878,
"max": 0.4522216022014618,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.16602230072021484,
"min": 0.16602230072021484,
"max": 3.16555118560791,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 609.68,
"min": 609.68,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30484.0,
"min": 15984.0,
"max": 33922.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.9101759646832943,
"min": -1.0000000521540642,
"max": 0.9101759646832943,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 45.508798234164715,
"min": -32.000001668930054,
"max": 45.508798234164715,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.9101759646832943,
"min": -1.0000000521540642,
"max": 0.9101759646832943,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 45.508798234164715,
"min": -32.000001668930054,
"max": 45.508798234164715,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.07606960660777987,
"min": 0.07606960660777987,
"max": 8.988390937447548,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.803480330388993,
"min": 3.736572267836891,
"max": 143.81425499916077,
"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": "1660088588",
"python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-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": "1660090551"
},
"total": 1962.7637415150002,
"count": 1,
"self": 0.4828909350003414,
"children": {
"run_training.setup": {
"total": 0.042640785000003234,
"count": 1,
"self": 0.042640785000003234
},
"TrainerController.start_learning": {
"total": 1962.2382097949999,
"count": 1,
"self": 1.3612930209847036,
"children": {
"TrainerController._reset_env": {
"total": 9.941774627999962,
"count": 1,
"self": 9.941774627999962
},
"TrainerController.advance": {
"total": 1950.8428995670147,
"count": 63366,
"self": 1.4818707500580786,
"children": {
"env_step": {
"total": 1235.5351816630027,
"count": 63366,
"self": 1127.1270648160214,
"children": {
"SubprocessEnvManager._take_step": {
"total": 107.67063594498734,
"count": 63366,
"self": 4.7632961079904135,
"children": {
"TorchPolicy.evaluate": {
"total": 102.90733983699693,
"count": 62568,
"self": 35.322871082947245,
"children": {
"TorchPolicy.sample_actions": {
"total": 67.58446875404968,
"count": 62568,
"self": 67.58446875404968
}
}
}
}
},
"workers": {
"total": 0.7374809019939903,
"count": 63366,
"self": 0.0,
"children": {
"worker_root": {
"total": 1958.2127912670126,
"count": 63366,
"is_parallel": true,
"self": 935.5557843619393,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005451580999988437,
"count": 1,
"is_parallel": true,
"self": 0.003598217000103432,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018533639998850049,
"count": 8,
"is_parallel": true,
"self": 0.0018533639998850049
}
}
},
"UnityEnvironment.step": {
"total": 0.05165570500003014,
"count": 1,
"is_parallel": true,
"self": 0.0005141319999211191,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004980549999800132,
"count": 1,
"is_parallel": true,
"self": 0.0004980549999800132
},
"communicator.exchange": {
"total": 0.04887545000008231,
"count": 1,
"is_parallel": true,
"self": 0.04887545000008231
},
"steps_from_proto": {
"total": 0.0017680680000466964,
"count": 1,
"is_parallel": true,
"self": 0.0004853980001371383,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001282669999909558,
"count": 8,
"is_parallel": true,
"self": 0.001282669999909558
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1022.6570069050732,
"count": 63365,
"is_parallel": true,
"self": 27.460449131097675,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.046237155980748,
"count": 63365,
"is_parallel": true,
"self": 24.046237155980748
},
"communicator.exchange": {
"total": 876.0644355899757,
"count": 63365,
"is_parallel": true,
"self": 876.0644355899757
},
"steps_from_proto": {
"total": 95.0858850280191,
"count": 63365,
"is_parallel": true,
"self": 23.720250741921177,
"children": {
"_process_rank_one_or_two_observation": {
"total": 71.36563428609793,
"count": 506920,
"is_parallel": true,
"self": 71.36563428609793
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 713.825847153954,
"count": 63366,
"self": 2.613098152948851,
"children": {
"process_trajectory": {
"total": 168.66315415400334,
"count": 63366,
"self": 168.459523092003,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20363106200034053,
"count": 2,
"self": 0.20363106200034053
}
}
},
"_update_policy": {
"total": 542.5495948470018,
"count": 435,
"self": 214.3418086120431,
"children": {
"TorchPPOOptimizer.update": {
"total": 328.2077862349587,
"count": 22878,
"self": 328.2077862349587
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2770001376338769e-06,
"count": 1,
"self": 1.2770001376338769e-06
},
"TrainerController._save_models": {
"total": 0.09224130200027503,
"count": 1,
"self": 0.0016490870002598967,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09059221500001513,
"count": 1,
"self": 0.09059221500001513
}
}
}
}
}
}
}