AMfeta99's picture
First Push
4c3b230
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8775478601455688,
"min": 0.8775478601455688,
"max": 2.864198684692383,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8398.1328125,
"min": 8398.1328125,
"max": 29332.2578125,
"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": 12.920686721801758,
"min": 0.42631134390830994,
"max": 12.920686721801758,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2519.533935546875,
"min": 82.70439910888672,
"max": 2597.923583984375,
"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.Losses.PolicyLoss.mean": {
"value": 0.06278686012599649,
"min": 0.06202666314029735,
"max": 0.07283243830598247,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25114744050398596,
"min": 0.2481066525611894,
"max": 0.3621439012691981,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18790862687370358,
"min": 0.10888996581642833,
"max": 0.27310771772674486,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7516345074948143,
"min": 0.43555986326571333,
"max": 1.3249135186859204,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.477272727272727,
"min": 3.1363636363636362,
"max": 25.672727272727272,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1121.0,
"min": 138.0,
"max": 1412.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.477272727272727,
"min": 3.1363636363636362,
"max": 25.672727272727272,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1121.0,
"min": 138.0,
"max": 1412.0,
"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": "1700126756",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1700127420"
},
"total": 664.3717232340001,
"count": 1,
"self": 0.5286285520001002,
"children": {
"run_training.setup": {
"total": 0.19130941800005985,
"count": 1,
"self": 0.19130941800005985
},
"TrainerController.start_learning": {
"total": 663.651785264,
"count": 1,
"self": 0.9850757420008449,
"children": {
"TrainerController._reset_env": {
"total": 2.0790845420000323,
"count": 1,
"self": 2.0790845420000323
},
"TrainerController.advance": {
"total": 660.483861266999,
"count": 18203,
"self": 0.4520729579927547,
"children": {
"env_step": {
"total": 660.0317883090063,
"count": 18203,
"self": 519.9436150080195,
"children": {
"SubprocessEnvManager._take_step": {
"total": 139.63538358199696,
"count": 18203,
"self": 2.8389756639971893,
"children": {
"TorchPolicy.evaluate": {
"total": 136.79640791799977,
"count": 18203,
"self": 136.79640791799977
}
}
},
"workers": {
"total": 0.452789718989834,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 661.1957767209824,
"count": 18203,
"is_parallel": true,
"self": 304.80010165298324,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008107129999984863,
"count": 1,
"is_parallel": true,
"self": 0.005687034999937168,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002420095000047695,
"count": 10,
"is_parallel": true,
"self": 0.002420095000047695
}
}
},
"UnityEnvironment.step": {
"total": 0.06917883400001301,
"count": 1,
"is_parallel": true,
"self": 0.0007551290000264999,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005260269999780576,
"count": 1,
"is_parallel": true,
"self": 0.0005260269999780576
},
"communicator.exchange": {
"total": 0.06552359099998739,
"count": 1,
"is_parallel": true,
"self": 0.06552359099998739
},
"steps_from_proto": {
"total": 0.0023740870000210634,
"count": 1,
"is_parallel": true,
"self": 0.0005279680000285225,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001846118999992541,
"count": 10,
"is_parallel": true,
"self": 0.001846118999992541
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 356.39567506799915,
"count": 18202,
"is_parallel": true,
"self": 15.533750624048821,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.914305880952384,
"count": 18202,
"is_parallel": true,
"self": 7.914305880952384
},
"communicator.exchange": {
"total": 284.12713422199624,
"count": 18202,
"is_parallel": true,
"self": 284.12713422199624
},
"steps_from_proto": {
"total": 48.8204843410017,
"count": 18202,
"is_parallel": true,
"self": 10.011290057043539,
"children": {
"_process_rank_one_or_two_observation": {
"total": 38.80919428395816,
"count": 182020,
"is_parallel": true,
"self": 38.80919428395816
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00022375100002136605,
"count": 1,
"self": 0.00022375100002136605,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 653.7344460530488,
"count": 699299,
"is_parallel": true,
"self": 18.483298010055023,
"children": {
"process_trajectory": {
"total": 355.5833301149936,
"count": 699299,
"is_parallel": true,
"self": 354.95119791099364,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6321322039999586,
"count": 4,
"is_parallel": true,
"self": 0.6321322039999586
}
}
},
"_update_policy": {
"total": 279.6678179280002,
"count": 90,
"is_parallel": true,
"self": 90.25747180100552,
"children": {
"TorchPPOOptimizer.update": {
"total": 189.41034612699468,
"count": 4587,
"is_parallel": true,
"self": 189.41034612699468
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10353996200001347,
"count": 1,
"self": 0.0012564349999593105,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10228352700005416,
"count": 1,
"self": 0.10228352700005416
}
}
}
}
}
}
}