ppo-Pyramids / run_logs /timers.json
LMrilo's picture
Push to hub model
dfe75e5 verified
raw
history blame
18.8 kB
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.1275058537721634,
"min": 0.12055564671754837,
"max": 1.4623150825500488,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 3863.9375,
"min": 3580.0205078125,
"max": 44360.7890625,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999992.0,
"min": 29996.0,
"max": 2999992.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999992.0,
"min": 29996.0,
"max": 2999992.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.6998583674430847,
"min": -0.06114347651600838,
"max": 0.8723020553588867,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 205.75836181640625,
"min": -14.674434661865234,
"max": 261.69061279296875,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.016107860952615738,
"min": -0.017617594450712204,
"max": 0.38243308663368225,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 4.735711097717285,
"min": -4.791985511779785,
"max": 91.01907348632812,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06885793464284183,
"min": 0.06317883936779774,
"max": 0.07548449028884838,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0328690196426276,
"min": 0.5163451832429448,
"max": 1.0779327518345476,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.013694679365208786,
"min": 0.000677118099624016,
"max": 0.01715445754450716,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2054201904781318,
"min": 0.009479653394736224,
"max": 0.24016240562310023,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.4929728357088865e-06,
"min": 1.4929728357088865e-06,
"max": 0.00029838354339596195,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.2394592535633297e-05,
"min": 2.2394592535633297e-05,
"max": 0.004011646062784666,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10049762444444445,
"min": 0.10049762444444445,
"max": 0.19946118095238097,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.5074643666666667,
"min": 1.3962282666666668,
"max": 2.8124822666666667,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 5.9712681999999925e-05,
"min": 5.9712681999999925e-05,
"max": 0.009946171977142856,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0008956902299999988,
"min": 0.0008956902299999988,
"max": 0.1337278118,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.008002572692930698,
"min": 0.00762457400560379,
"max": 0.5965490937232971,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.12003858387470245,
"min": 0.10674403607845306,
"max": 4.175843715667725,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 255.83333333333334,
"min": 206.32167832167832,
"max": 995.9310344827586,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30700.0,
"min": 16795.0,
"max": 32979.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6274599832793077,
"min": -0.9277172941586067,
"max": 1.7890735214904827,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 195.29519799351692,
"min": -26.903801530599594,
"max": 252.1455978229642,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6274599832793077,
"min": -0.9277172941586067,
"max": 1.7890735214904827,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 195.29519799351692,
"min": -26.903801530599594,
"max": 252.1455978229642,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.021466122132612023,
"min": 0.018882575751275808,
"max": 11.62093585729599,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.575934655913443,
"min": 2.4290211769548478,
"max": 197.55590957403183,
"count": 100
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1717746277",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1717753958"
},
"total": 7680.571906839999,
"count": 1,
"self": 0.4984946269996726,
"children": {
"run_training.setup": {
"total": 0.07036302099999148,
"count": 1,
"self": 0.07036302099999148
},
"TrainerController.start_learning": {
"total": 7680.003049192,
"count": 1,
"self": 4.488885655246122,
"children": {
"TrainerController._reset_env": {
"total": 4.840348274000007,
"count": 1,
"self": 4.840348274000007
},
"TrainerController.advance": {
"total": 7670.583884144755,
"count": 195208,
"self": 4.566027422592015,
"children": {
"env_step": {
"total": 5665.319849655057,
"count": 195208,
"self": 5249.494693577157,
"children": {
"SubprocessEnvManager._take_step": {
"total": 413.07185704604535,
"count": 195208,
"self": 14.732412632202227,
"children": {
"TorchPolicy.evaluate": {
"total": 398.3394444138431,
"count": 187563,
"self": 398.3394444138431
}
}
},
"workers": {
"total": 2.7532990318550503,
"count": 195208,
"self": 0.0,
"children": {
"worker_root": {
"total": 7662.198392925113,
"count": 195208,
"is_parallel": true,
"self": 2807.9524025382243,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007551720000009254,
"count": 1,
"is_parallel": true,
"self": 0.0035574240000073587,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003994296000001896,
"count": 8,
"is_parallel": true,
"self": 0.003994296000001896
}
}
},
"UnityEnvironment.step": {
"total": 0.052356160000016416,
"count": 1,
"is_parallel": true,
"self": 0.0006357870000215371,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004809170000044105,
"count": 1,
"is_parallel": true,
"self": 0.0004809170000044105
},
"communicator.exchange": {
"total": 0.049544561000004705,
"count": 1,
"is_parallel": true,
"self": 0.049544561000004705
},
"steps_from_proto": {
"total": 0.0016948949999857632,
"count": 1,
"is_parallel": true,
"self": 0.000342662000036853,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013522329999489102,
"count": 8,
"is_parallel": true,
"self": 0.0013522329999489102
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 4854.2459903868885,
"count": 195207,
"is_parallel": true,
"self": 106.2768017306571,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 71.16893247094706,
"count": 195207,
"is_parallel": true,
"self": 71.16893247094706
},
"communicator.exchange": {
"total": 4375.628440348113,
"count": 195207,
"is_parallel": true,
"self": 4375.628440348113
},
"steps_from_proto": {
"total": 301.1718158371715,
"count": 195207,
"is_parallel": true,
"self": 61.99049672068338,
"children": {
"_process_rank_one_or_two_observation": {
"total": 239.1813191164881,
"count": 1561656,
"is_parallel": true,
"self": 239.1813191164881
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 2000.6980070671057,
"count": 195208,
"self": 9.129185914231812,
"children": {
"process_trajectory": {
"total": 415.6658417478768,
"count": 195208,
"self": 414.906592412877,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7592493349998222,
"count": 6,
"self": 0.7592493349998222
}
}
},
"_update_policy": {
"total": 1575.902979404997,
"count": 1403,
"self": 932.4414969050497,
"children": {
"TorchPPOOptimizer.update": {
"total": 643.4614824999474,
"count": 68376,
"self": 643.4614824999474
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0869998732232489e-06,
"count": 1,
"self": 1.0869998732232489e-06
},
"TrainerController._save_models": {
"total": 0.0899300309993123,
"count": 1,
"self": 0.0015448469994225889,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0883851839998897,
"count": 1,
"self": 0.0883851839998897
}
}
}
}
}
}
}