ppo-Pyramids / run_logs /timers.json
iubeda's picture
v1 Pyramids
efe3809
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5186700820922852,
"min": 0.5186700820922852,
"max": 1.4641852378845215,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 15468.81640625,
"min": 15468.81640625,
"max": 44417.5234375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989879.0,
"min": 29952.0,
"max": 989879.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989879.0,
"min": 29952.0,
"max": 989879.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.2242436707019806,
"min": -0.10230271518230438,
"max": 0.30391162633895874,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 58.07910919189453,
"min": -24.55265235900879,
"max": 79.62484741210938,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.27450230717658997,
"min": -0.27450230717658997,
"max": 0.44274553656578064,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -71.09609985351562,
"min": -71.09609985351562,
"max": 104.93069458007812,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06775121990427752,
"min": 0.0651649349612945,
"max": 0.07272711539385456,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9485170786598852,
"min": 0.4800219613019275,
"max": 1.071894182241094,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.033572408460756945,
"min": 0.00012835025828943767,
"max": 0.033572408460756945,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.47001371845059725,
"min": 0.0016685533577626896,
"max": 0.47001371845059725,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.5184189224642915e-06,
"min": 7.5184189224642915e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010525786491450009,
"min": 0.00010525786491450009,
"max": 0.0035069648310118006,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10250610714285714,
"min": 0.10250610714285714,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4350855,
"min": 1.3691136000000002,
"max": 2.5689881999999997,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002603601035714288,
"min": 0.0002603601035714288,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003645041450000003,
"min": 0.003645041450000003,
"max": 0.11692192117999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01182196568697691,
"min": 0.01182196568697691,
"max": 0.4981929659843445,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.16550752520561218,
"min": 0.16550752520561218,
"max": 3.4873507022857666,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 603.3703703703703,
"min": 545.1428571428571,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 32582.0,
"min": 15984.0,
"max": 32673.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.0261703288113628,
"min": -1.0000000521540642,
"max": 1.2047892568100775,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 55.4131977558136,
"min": -32.000001668930054,
"max": 67.46819838136435,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.0261703288113628,
"min": -1.0000000521540642,
"max": 1.2047892568100775,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 55.4131977558136,
"min": -32.000001668930054,
"max": 67.46819838136435,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.07396067515434913,
"min": 0.06892869181839549,
"max": 11.127175770699978,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.993876458334853,
"min": 3.543178327206988,
"max": 178.03481233119965,
"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": "1676674876",
"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": "1.21.6",
"end_time_seconds": "1676678098"
},
"total": 3221.833727874,
"count": 1,
"self": 1.2905063709995375,
"children": {
"run_training.setup": {
"total": 0.14645346700035589,
"count": 1,
"self": 0.14645346700035589
},
"TrainerController.start_learning": {
"total": 3220.396768036,
"count": 1,
"self": 2.260227614100586,
"children": {
"TrainerController._reset_env": {
"total": 5.562130258999787,
"count": 1,
"self": 5.562130258999787
},
"TrainerController.advance": {
"total": 3212.4274911079,
"count": 63336,
"self": 2.6639651949826657,
"children": {
"env_step": {
"total": 2011.8585710979223,
"count": 63336,
"self": 1870.5639805182218,
"children": {
"SubprocessEnvManager._take_step": {
"total": 139.7974889637535,
"count": 63336,
"self": 6.645931182665663,
"children": {
"TorchPolicy.evaluate": {
"total": 133.15155778108783,
"count": 62559,
"self": 29.31285915099943,
"children": {
"TorchPolicy.sample_actions": {
"total": 103.8386986300884,
"count": 62559,
"self": 103.8386986300884
}
}
}
}
},
"workers": {
"total": 1.497101615947031,
"count": 63336,
"self": 0.0,
"children": {
"worker_root": {
"total": 3213.8114188870577,
"count": 63336,
"is_parallel": true,
"self": 1515.2142801911705,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0032480509999004425,
"count": 1,
"is_parallel": true,
"self": 0.0013054609989922028,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019425900009082397,
"count": 8,
"is_parallel": true,
"self": 0.0019425900009082397
}
}
},
"UnityEnvironment.step": {
"total": 0.10850649500025611,
"count": 1,
"is_parallel": true,
"self": 0.000646462000986503,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000534324000000197,
"count": 1,
"is_parallel": true,
"self": 0.000534324000000197
},
"communicator.exchange": {
"total": 0.10519388299962884,
"count": 1,
"is_parallel": true,
"self": 0.10519388299962884
},
"steps_from_proto": {
"total": 0.0021318259996405686,
"count": 1,
"is_parallel": true,
"self": 0.0005266709986244678,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016051550010161009,
"count": 8,
"is_parallel": true,
"self": 0.0016051550010161009
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1698.5971386958872,
"count": 63335,
"is_parallel": true,
"self": 44.587406773642215,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 25.766157510093763,
"count": 63335,
"is_parallel": true,
"self": 25.766157510093763
},
"communicator.exchange": {
"total": 1483.2898429969973,
"count": 63335,
"is_parallel": true,
"self": 1483.2898429969973
},
"steps_from_proto": {
"total": 144.95373141515392,
"count": 63335,
"is_parallel": true,
"self": 33.786501638131995,
"children": {
"_process_rank_one_or_two_observation": {
"total": 111.16722977702193,
"count": 506680,
"is_parallel": true,
"self": 111.16722977702193
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1197.904954814995,
"count": 63336,
"self": 4.208825963160052,
"children": {
"process_trajectory": {
"total": 213.8430898768347,
"count": 63336,
"self": 213.57587364183564,
"children": {
"RLTrainer._checkpoint": {
"total": 0.26721623499906855,
"count": 2,
"self": 0.26721623499906855
}
}
},
"_update_policy": {
"total": 979.8530389750003,
"count": 440,
"self": 270.3229545380527,
"children": {
"TorchPPOOptimizer.update": {
"total": 709.5300844369476,
"count": 22857,
"self": 709.5300844369476
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.491000148234889e-06,
"count": 1,
"self": 1.491000148234889e-06
},
"TrainerController._save_models": {
"total": 0.14691756399952283,
"count": 1,
"self": 0.002513235000151326,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1444043289993715,
"count": 1,
"self": 0.1444043289993715
}
}
}
}
}
}
}