prepsyched's picture
First Push
b6d619f
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8263290524482727,
"min": 0.8263290524482727,
"max": 2.8554491996765137,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7953.4169921875,
"min": 7953.4169921875,
"max": 29274.06640625,
"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": 12.968354225158691,
"min": 0.42121636867523193,
"max": 12.968354225158691,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2528.8291015625,
"min": 81.71597290039062,
"max": 2642.541259765625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07221894189327335,
"min": 0.062002496362073736,
"max": 0.07444762885964284,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2888757675730934,
"min": 0.2645279543175289,
"max": 0.3528868874696747,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2177541883406686,
"min": 0.1278750106073715,
"max": 0.28603080141485904,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8710167533626744,
"min": 0.511500042429486,
"max": 1.3841947521649154,
"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": 3.6818181818181817,
"max": 25.636363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1121.0,
"min": 162.0,
"max": 1410.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.477272727272727,
"min": 3.6818181818181817,
"max": 25.636363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1121.0,
"min": 162.0,
"max": 1410.0,
"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": "1682487369",
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --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": "1682487877"
},
"total": 507.499546348,
"count": 1,
"self": 0.9565561940000293,
"children": {
"run_training.setup": {
"total": 0.1296906540000009,
"count": 1,
"self": 0.1296906540000009
},
"TrainerController.start_learning": {
"total": 506.4132995,
"count": 1,
"self": 0.6952466499934076,
"children": {
"TrainerController._reset_env": {
"total": 5.460698605999994,
"count": 1,
"self": 5.460698605999994
},
"TrainerController.advance": {
"total": 500.0397007670067,
"count": 18223,
"self": 0.3587030810130045,
"children": {
"env_step": {
"total": 499.6809976859937,
"count": 18223,
"self": 367.8427802019789,
"children": {
"SubprocessEnvManager._take_step": {
"total": 131.50212115099748,
"count": 18223,
"self": 2.0876979709971124,
"children": {
"TorchPolicy.evaluate": {
"total": 129.41442318000037,
"count": 18223,
"self": 129.41442318000037
}
}
},
"workers": {
"total": 0.33609633301733766,
"count": 18223,
"self": 0.0,
"children": {
"worker_root": {
"total": 504.4696960559984,
"count": 18223,
"is_parallel": true,
"self": 230.1250537219957,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.010702003000005789,
"count": 1,
"is_parallel": true,
"self": 0.00852820900001916,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021737939999866285,
"count": 10,
"is_parallel": true,
"self": 0.0021737939999866285
}
}
},
"UnityEnvironment.step": {
"total": 0.03902452300002324,
"count": 1,
"is_parallel": true,
"self": 0.0006979690000434857,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004503149999663947,
"count": 1,
"is_parallel": true,
"self": 0.0004503149999663947
},
"communicator.exchange": {
"total": 0.035745260999988204,
"count": 1,
"is_parallel": true,
"self": 0.035745260999988204
},
"steps_from_proto": {
"total": 0.002130978000025152,
"count": 1,
"is_parallel": true,
"self": 0.0004481180001221219,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016828599999030303,
"count": 10,
"is_parallel": true,
"self": 0.0016828599999030303
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 274.3446423340027,
"count": 18222,
"is_parallel": true,
"self": 10.964036137002779,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.853154638993772,
"count": 18222,
"is_parallel": true,
"self": 5.853154638993772
},
"communicator.exchange": {
"total": 222.53799070200375,
"count": 18222,
"is_parallel": true,
"self": 222.53799070200375
},
"steps_from_proto": {
"total": 34.98946085600238,
"count": 18222,
"is_parallel": true,
"self": 7.24336234601293,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.74609850998945,
"count": 182220,
"is_parallel": true,
"self": 27.74609850998945
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00018833999990874872,
"count": 1,
"self": 0.00018833999990874872,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 496.15999412302943,
"count": 462892,
"is_parallel": true,
"self": 11.563213765081173,
"children": {
"process_trajectory": {
"total": 275.8663083969487,
"count": 462892,
"is_parallel": true,
"self": 274.6521739059486,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2141344910000953,
"count": 4,
"is_parallel": true,
"self": 1.2141344910000953
}
}
},
"_update_policy": {
"total": 208.73047196099958,
"count": 90,
"is_parallel": true,
"self": 77.2924330500008,
"children": {
"TorchPPOOptimizer.update": {
"total": 131.43803891099878,
"count": 4587,
"is_parallel": true,
"self": 131.43803891099878
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.2174651369999765,
"count": 1,
"self": 0.0011876599999141035,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2162774770000624,
"count": 1,
"self": 0.2162774770000624
}
}
}
}
}
}
}