{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.38682326674461365,
"min": 0.35990023612976074,
"max": 1.3901994228363037,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 11530.427734375,
"min": 10699.1142578125,
"max": 42173.08984375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989995.0,
"min": 29952.0,
"max": 989995.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989995.0,
"min": 29952.0,
"max": 989995.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7398255467414856,
"min": -0.08419597893953323,
"max": 0.7526828646659851,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 216.029052734375,
"min": -20.207035064697266,
"max": 220.5360870361328,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.00451322877779603,
"min": -0.0188564732670784,
"max": 0.2553403079509735,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 1.3178627490997314,
"min": -5.242099761962891,
"max": 61.53701400756836,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06877794230089578,
"min": 0.06544373470907365,
"max": 0.07368929681076712,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9628911922125409,
"min": 0.5106771345708276,
"max": 1.0658852602355182,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015926785089497204,
"min": 0.0008651735148203711,
"max": 0.015958561030510326,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22297499125296083,
"min": 0.011247255692664824,
"max": 0.2235711103324623,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.714340285728573e-06,
"min": 7.714340285728573e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010800076400020001,
"min": 0.00010800076400020001,
"max": 0.0036328477890507993,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1025714142857143,
"min": 0.1025714142857143,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4359998000000003,
"min": 1.3886848,
"max": 2.6109492000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002668842871428572,
"min": 0.0002668842871428572,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003736380020000001,
"min": 0.003736380020000001,
"max": 0.12111382508000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010567950084805489,
"min": 0.010347140021622181,
"max": 0.5105068683624268,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.14795130491256714,
"min": 0.14485995471477509,
"max": 3.5735480785369873,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 258.62280701754383,
"min": 248.29310344827587,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29483.0,
"min": 15984.0,
"max": 32153.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7240869382801263,
"min": -1.0000000521540642,
"max": 1.7342869434019794,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 198.26999790221453,
"min": -29.619201637804508,
"max": 199.44299849122763,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7240869382801263,
"min": -1.0000000521540642,
"max": 1.7342869434019794,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 198.26999790221453,
"min": -29.619201637804508,
"max": 199.44299849122763,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.028475601412608978,
"min": 0.027919542935927417,
"max": 10.732130581513047,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.2746941624500323,
"min": 3.210747437631653,
"max": 171.71408930420876,
"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": "1681548181",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1681550526"
},
"total": 2345.347111204,
"count": 1,
"self": 0.6384944810001798,
"children": {
"run_training.setup": {
"total": 0.11066692299993974,
"count": 1,
"self": 0.11066692299993974
},
"TrainerController.start_learning": {
"total": 2344.5979498,
"count": 1,
"self": 1.6792850550000367,
"children": {
"TrainerController._reset_env": {
"total": 4.154924062999953,
"count": 1,
"self": 4.154924062999953
},
"TrainerController.advance": {
"total": 2338.6677385310004,
"count": 64109,
"self": 1.8379834430384108,
"children": {
"env_step": {
"total": 1695.2405459250072,
"count": 64109,
"self": 1571.2358920180322,
"children": {
"SubprocessEnvManager._take_step": {
"total": 122.9853349839542,
"count": 64109,
"self": 5.3714552129207505,
"children": {
"TorchPolicy.evaluate": {
"total": 117.61387977103345,
"count": 62549,
"self": 117.61387977103345
}
}
},
"workers": {
"total": 1.0193189230207054,
"count": 64109,
"self": 0.0,
"children": {
"worker_root": {
"total": 2338.5044776069467,
"count": 64109,
"is_parallel": true,
"self": 895.7648280429387,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004855481000049622,
"count": 1,
"is_parallel": true,
"self": 0.0034032579999347945,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014522230001148273,
"count": 8,
"is_parallel": true,
"self": 0.0014522230001148273
}
}
},
"UnityEnvironment.step": {
"total": 0.05214726299993799,
"count": 1,
"is_parallel": true,
"self": 0.0005782920000001468,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003576780000003055,
"count": 1,
"is_parallel": true,
"self": 0.0003576780000003055
},
"communicator.exchange": {
"total": 0.049399322999988726,
"count": 1,
"is_parallel": true,
"self": 0.049399322999988726
},
"steps_from_proto": {
"total": 0.0018119699999488148,
"count": 1,
"is_parallel": true,
"self": 0.0004187649998357301,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013932050001130847,
"count": 8,
"is_parallel": true,
"self": 0.0013932050001130847
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1442.739649564008,
"count": 64108,
"is_parallel": true,
"self": 34.777339685018205,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 25.936349550013688,
"count": 64108,
"is_parallel": true,
"self": 25.936349550013688
},
"communicator.exchange": {
"total": 1278.1960732510074,
"count": 64108,
"is_parallel": true,
"self": 1278.1960732510074
},
"steps_from_proto": {
"total": 103.82988707796846,
"count": 64108,
"is_parallel": true,
"self": 22.92938900298259,
"children": {
"_process_rank_one_or_two_observation": {
"total": 80.90049807498588,
"count": 512864,
"is_parallel": true,
"self": 80.90049807498588
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 641.5892091629547,
"count": 64109,
"self": 3.0745091119454173,
"children": {
"process_trajectory": {
"total": 117.86403199301083,
"count": 64109,
"self": 117.6572417730107,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20679022000012992,
"count": 2,
"self": 0.20679022000012992
}
}
},
"_update_policy": {
"total": 520.6506680579985,
"count": 455,
"self": 334.0515452749728,
"children": {
"TorchPPOOptimizer.update": {
"total": 186.59912278302568,
"count": 22764,
"self": 186.59912278302568
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.269997462979518e-07,
"count": 1,
"self": 9.269997462979518e-07
},
"TrainerController._save_models": {
"total": 0.09600122399979227,
"count": 1,
"self": 0.0014548169997397054,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09454640700005257,
"count": 1,
"self": 0.09454640700005257
}
}
}
}
}
}
}