ppo-Pyramids / run_logs /timers.json
mavorizey's picture
First push
e1a7f03 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3144925534725189,
"min": 0.31073474884033203,
"max": 1.473048448562622,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 9349.234375,
"min": 9349.234375,
"max": 44686.3984375,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989992.0,
"min": 29989.0,
"max": 989992.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989992.0,
"min": 29989.0,
"max": 989992.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7319541573524475,
"min": -0.1314724236726761,
"max": 0.7363229393959045,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 217.390380859375,
"min": -31.290435791015625,
"max": 217.390380859375,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.0006318936357274652,
"min": -0.016731685027480125,
"max": 0.2533068358898163,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 0.18767240643501282,
"min": -4.684871673583984,
"max": 60.28702926635742,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0712668575156602,
"min": 0.06539950154277,
"max": 0.07334123379301413,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9977360052192428,
"min": 0.5112596604626508,
"max": 1.0567410459534228,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015745003085439316,
"min": 0.00186396052644333,
"max": 0.016792382623686285,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22043004319615042,
"min": 0.020736163388917837,
"max": 0.235093356731608,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.680590296978567e-06,
"min": 7.680590296978567e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010752826415769995,
"min": 0.00010752826415769995,
"max": 0.0037581424472859,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10256016428571427,
"min": 0.10256016428571427,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4358422999999998,
"min": 1.3886848,
"max": 2.7525998,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002657604121428571,
"min": 0.0002657604121428571,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003720645769999999,
"min": 0.003720645769999999,
"max": 0.12528613858999998,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.013174067251384258,
"min": 0.01293072197586298,
"max": 0.3784453272819519,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.18443694710731506,
"min": 0.18103010952472687,
"max": 2.6491172313690186,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 255.675,
"min": 245.0,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30681.0,
"min": 16788.0,
"max": 32976.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7287730933362697,
"min": -0.9999871489501768,
"max": 1.7287730933362697,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 205.7239981070161,
"min": -30.999601617455482,
"max": 205.7239981070161,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7287730933362697,
"min": -0.9999871489501768,
"max": 1.7287730933362697,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 205.7239981070161,
"min": -30.999601617455482,
"max": 205.7239981070161,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.034463045473227386,
"min": 0.034463045473227386,
"max": 7.005180153338348,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.101102411314059,
"min": 4.025156122399494,
"max": 119.08806260675192,
"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": "1745269822",
"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": "1745272249"
},
"total": 2426.7964040569996,
"count": 1,
"self": 0.5267342529996313,
"children": {
"run_training.setup": {
"total": 0.020553553999889118,
"count": 1,
"self": 0.020553553999889118
},
"TrainerController.start_learning": {
"total": 2426.24911625,
"count": 1,
"self": 1.500676917101373,
"children": {
"TrainerController._reset_env": {
"total": 2.838472616999752,
"count": 1,
"self": 2.838472616999752
},
"TrainerController.advance": {
"total": 2421.7864761288984,
"count": 64292,
"self": 1.5445690288161131,
"children": {
"env_step": {
"total": 1710.3731196360031,
"count": 64292,
"self": 1547.404362252063,
"children": {
"SubprocessEnvManager._take_step": {
"total": 162.10117333614744,
"count": 64292,
"self": 4.948752987212174,
"children": {
"TorchPolicy.evaluate": {
"total": 157.15242034893527,
"count": 62546,
"self": 157.15242034893527
}
}
},
"workers": {
"total": 0.8675840477926613,
"count": 64292,
"self": 0.0,
"children": {
"worker_root": {
"total": 2420.6579418950205,
"count": 64292,
"is_parallel": true,
"self": 995.8653193639484,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0025860699997792835,
"count": 1,
"is_parallel": true,
"self": 0.0007714909997957875,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001814578999983496,
"count": 8,
"is_parallel": true,
"self": 0.001814578999983496
}
}
},
"UnityEnvironment.step": {
"total": 0.08092041700001573,
"count": 1,
"is_parallel": true,
"self": 0.0005749599995397148,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004909079998469679,
"count": 1,
"is_parallel": true,
"self": 0.0004909079998469679
},
"communicator.exchange": {
"total": 0.07802524100043229,
"count": 1,
"is_parallel": true,
"self": 0.07802524100043229
},
"steps_from_proto": {
"total": 0.001829308000196761,
"count": 1,
"is_parallel": true,
"self": 0.000481760999718972,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001347547000477789,
"count": 8,
"is_parallel": true,
"self": 0.001347547000477789
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1424.792622531072,
"count": 64291,
"is_parallel": true,
"self": 32.33048573305132,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.586858076871067,
"count": 64291,
"is_parallel": true,
"self": 23.586858076871067
},
"communicator.exchange": {
"total": 1268.9024541200088,
"count": 64291,
"is_parallel": true,
"self": 1268.9024541200088
},
"steps_from_proto": {
"total": 99.97282460114093,
"count": 64291,
"is_parallel": true,
"self": 20.51124178786904,
"children": {
"_process_rank_one_or_two_observation": {
"total": 79.46158281327189,
"count": 514328,
"is_parallel": true,
"self": 79.46158281327189
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 709.8687874640791,
"count": 64292,
"self": 2.9613332280350733,
"children": {
"process_trajectory": {
"total": 140.29794609504097,
"count": 64292,
"self": 140.036024672042,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2619214229989666,
"count": 2,
"self": 0.2619214229989666
}
}
},
"_update_policy": {
"total": 566.6095081410031,
"count": 457,
"self": 313.6969033759706,
"children": {
"TorchPPOOptimizer.update": {
"total": 252.91260476503248,
"count": 22788,
"self": 252.91260476503248
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3980006769998e-06,
"count": 1,
"self": 1.3980006769998e-06
},
"TrainerController._save_models": {
"total": 0.12348918899988348,
"count": 1,
"self": 0.0018925029999081744,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1215966859999753,
"count": 1,
"self": 0.1215966859999753
}
}
}
}
}
}
}