114-HK's picture
First Push
372ce46 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8518984317779541,
"min": 0.8437926769256592,
"max": 2.8137638568878174,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8096.44287109375,
"min": 8096.44287109375,
"max": 28722.90234375,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.789359092712402,
"min": 0.3410358130931854,
"max": 12.789359092712402,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2493.925048828125,
"min": 66.16094970703125,
"max": 2607.31640625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06305708752776862,
"min": 0.06293257170235686,
"max": 0.07098333742206331,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2522283501110745,
"min": 0.2522283501110745,
"max": 0.35491668711031654,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2240016872939818,
"min": 0.13631998371505796,
"max": 0.29378066737862196,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8960067491759272,
"min": 0.5452799348602319,
"max": 1.3838632626130298,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000007e-06,
"min": 8.082097306000007e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400003e-05,
"min": 3.232838922400003e-05,
"max": 0.0013851600382800001,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10377160000000002,
"min": 0.10377160000000002,
"max": 0.23621159999999997,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4150864000000001,
"min": 0.4150864000000001,
"max": 1.146408,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.004864970599999999,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828000000003,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.09090909090909,
"min": 4.181818181818182,
"max": 25.490909090909092,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1104.0,
"min": 184.0,
"max": 1402.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.09090909090909,
"min": 4.181818181818182,
"max": 25.490909090909092,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1104.0,
"min": 184.0,
"max": 1402.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1740066448",
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1740066910"
},
"total": 462.15345461899983,
"count": 1,
"self": 0.4369872539998596,
"children": {
"run_training.setup": {
"total": 0.02397072799999478,
"count": 1,
"self": 0.02397072799999478
},
"TrainerController.start_learning": {
"total": 461.692496637,
"count": 1,
"self": 0.3434742859958533,
"children": {
"TrainerController._reset_env": {
"total": 2.930825700000014,
"count": 1,
"self": 2.930825700000014
},
"TrainerController.advance": {
"total": 458.31111220100433,
"count": 18192,
"self": 0.3688538659766891,
"children": {
"env_step": {
"total": 304.27807202702434,
"count": 18192,
"self": 230.81607807302908,
"children": {
"SubprocessEnvManager._take_step": {
"total": 73.25093069800118,
"count": 18192,
"self": 1.2891592759942796,
"children": {
"TorchPolicy.evaluate": {
"total": 71.9617714220069,
"count": 18192,
"self": 71.9617714220069
}
}
},
"workers": {
"total": 0.21106325599407683,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 460.263038051987,
"count": 18192,
"is_parallel": true,
"self": 258.0637268579949,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005314815000019735,
"count": 1,
"is_parallel": true,
"self": 0.0038142240000524907,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001500590999967244,
"count": 10,
"is_parallel": true,
"self": 0.001500590999967244
}
}
},
"UnityEnvironment.step": {
"total": 0.0396205069998814,
"count": 1,
"is_parallel": true,
"self": 0.0006639429998358537,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004125559999010875,
"count": 1,
"is_parallel": true,
"self": 0.0004125559999010875
},
"communicator.exchange": {
"total": 0.03654142599998522,
"count": 1,
"is_parallel": true,
"self": 0.03654142599998522
},
"steps_from_proto": {
"total": 0.0020025820001592365,
"count": 1,
"is_parallel": true,
"self": 0.0003732190000391711,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016293630001200654,
"count": 10,
"is_parallel": true,
"self": 0.0016293630001200654
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 202.19931119399212,
"count": 18191,
"is_parallel": true,
"self": 9.827855389998149,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.383947058996682,
"count": 18191,
"is_parallel": true,
"self": 5.383947058996682
},
"communicator.exchange": {
"total": 154.82574600101543,
"count": 18191,
"is_parallel": true,
"self": 154.82574600101543
},
"steps_from_proto": {
"total": 32.16176274398185,
"count": 18191,
"is_parallel": true,
"self": 5.743740156943659,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.418022587038195,
"count": 181910,
"is_parallel": true,
"self": 26.418022587038195
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 153.6641863080033,
"count": 18192,
"self": 0.40352304501129765,
"children": {
"process_trajectory": {
"total": 26.740501357991207,
"count": 18192,
"self": 26.296823433990994,
"children": {
"RLTrainer._checkpoint": {
"total": 0.44367792400021244,
"count": 4,
"self": 0.44367792400021244
}
}
},
"_update_policy": {
"total": 126.5201619050008,
"count": 90,
"self": 50.00746927599221,
"children": {
"TorchPPOOptimizer.update": {
"total": 76.5126926290086,
"count": 6116,
"self": 76.5126926290086
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5949999578879215e-06,
"count": 1,
"self": 1.5949999578879215e-06
},
"TrainerController._save_models": {
"total": 0.10708285499981685,
"count": 1,
"self": 0.0010191049996137735,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10606375000020307,
"count": 1,
"self": 0.10606375000020307
}
}
}
}
}
}
}