ARandomFrenchDev's picture
add : model v1
69a8cc3
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.3973889350891113,
"min": 2.3973889350891113,
"max": 2.877216100692749,
"count": 10
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 12236.2734375,
"min": 11668.0966796875,
"max": 14843.5576171875,
"count": 10
},
"SnowballTarget.Step.mean": {
"value": 49936.0,
"min": 4976.0,
"max": 49936.0,
"count": 10
},
"SnowballTarget.Step.sum": {
"value": 49936.0,
"min": 4976.0,
"max": 49936.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 3.5880813598632812,
"min": 0.1983867883682251,
"max": 3.5880813598632812,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 348.04388427734375,
"min": 19.243518829345703,
"max": 348.04388427734375,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 4378.0,
"min": 4378.0,
"max": 6567.0,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06701741381502692,
"min": 0.06270544963947888,
"max": 0.07574009277981103,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.13403482763005384,
"min": 0.12541089927895777,
"max": 0.20143494356820799,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1788221293804692,
"min": 0.07101749088478221,
"max": 0.19984403340255516,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.3576442587609384,
"min": 0.14203498176956442,
"max": 0.5995321002076655,
"count": 10
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.672809442400001e-05,
"min": 1.672809442400001e-05,
"max": 0.00028072800642399995,
"count": 10
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.345618884800002e-05,
"min": 3.345618884800002e-05,
"max": 0.000584784105072,
"count": 10
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.105576,
"min": 0.105576,
"max": 0.193576,
"count": 10
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.211152,
"min": 0.211152,
"max": 0.49492800000000003,
"count": 10
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0002882424000000002,
"min": 0.0002882424000000002,
"max": 0.004679442400000001,
"count": 10
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005764848000000004,
"min": 0.0005764848000000004,
"max": 0.009756907200000001,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 10.772727272727273,
"min": 2.9545454545454546,
"max": 10.772727272727273,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 237.0,
"min": 65.0,
"max": 351.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 8.618182044137608,
"min": 2.3636364205317064,
"max": 8.618182044137608,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 189.60000497102737,
"min": 52.00000125169754,
"max": 280.80000627040863,
"count": 10
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1675369793",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1675369924"
},
"total": 131.34410677999995,
"count": 1,
"self": 0.6372174449998056,
"children": {
"run_training.setup": {
"total": 0.10161595199997464,
"count": 1,
"self": 0.10161595199997464
},
"TrainerController.start_learning": {
"total": 130.60527338300017,
"count": 1,
"self": 0.2374818670039076,
"children": {
"TrainerController._reset_env": {
"total": 11.259369021000111,
"count": 1,
"self": 11.259369021000111
},
"TrainerController.advance": {
"total": 118.90640794599608,
"count": 4610,
"self": 0.081280063991926,
"children": {
"env_step": {
"total": 118.82512788200415,
"count": 4610,
"self": 81.845734482019,
"children": {
"SubprocessEnvManager._take_step": {
"total": 36.90533245299139,
"count": 4610,
"self": 0.39505681599780473,
"children": {
"TorchPolicy.evaluate": {
"total": 36.51027563699358,
"count": 4610,
"self": 7.880312316990057,
"children": {
"TorchPolicy.sample_actions": {
"total": 28.629963320003526,
"count": 4610,
"self": 28.629963320003526
}
}
}
}
},
"workers": {
"total": 0.07406094699376808,
"count": 4610,
"self": 0.0,
"children": {
"worker_root": {
"total": 130.00047968400827,
"count": 4610,
"is_parallel": true,
"self": 67.45645105400354,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006743988999915018,
"count": 1,
"is_parallel": true,
"self": 0.003973014999246516,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0027709740006685024,
"count": 10,
"is_parallel": true,
"self": 0.0027709740006685024
}
}
},
"UnityEnvironment.step": {
"total": 0.04604479099998571,
"count": 1,
"is_parallel": true,
"self": 0.00034276099995622644,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00022856700002193975,
"count": 1,
"is_parallel": true,
"self": 0.00022856700002193975
},
"communicator.exchange": {
"total": 0.043614354000055755,
"count": 1,
"is_parallel": true,
"self": 0.043614354000055755
},
"steps_from_proto": {
"total": 0.0018591089999517862,
"count": 1,
"is_parallel": true,
"self": 0.0004981810002391285,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013609279997126578,
"count": 10,
"is_parallel": true,
"self": 0.0013609279997126578
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 62.54402863000473,
"count": 4609,
"is_parallel": true,
"self": 2.2046534780017737,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 1.33372472200449,
"count": 4609,
"is_parallel": true,
"self": 1.33372472200449
},
"communicator.exchange": {
"total": 50.80246806499599,
"count": 4609,
"is_parallel": true,
"self": 50.80246806499599
},
"steps_from_proto": {
"total": 8.203182365002476,
"count": 4609,
"is_parallel": true,
"self": 1.8361947920009243,
"children": {
"_process_rank_one_or_two_observation": {
"total": 6.366987573001552,
"count": 46090,
"is_parallel": true,
"self": 6.366987573001552
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.194100006316148e-05,
"count": 1,
"self": 4.194100006316148e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 118.09674191093177,
"count": 106925,
"is_parallel": true,
"self": 2.677815956941231,
"children": {
"process_trajectory": {
"total": 69.06506294899077,
"count": 106925,
"is_parallel": true,
"self": 67.01251503299068,
"children": {
"RLTrainer._checkpoint": {
"total": 2.052547916000094,
"count": 5,
"is_parallel": true,
"self": 2.052547916000094
}
}
},
"_update_policy": {
"total": 46.353863004999766,
"count": 22,
"is_parallel": true,
"self": 16.343123554996055,
"children": {
"TorchPPOOptimizer.update": {
"total": 30.01073945000371,
"count": 1119,
"is_parallel": true,
"self": 30.01073945000371
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.2019726080000055,
"count": 1,
"self": 0.0010879159999603871,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2008846920000451,
"count": 1,
"self": 0.2008846920000451
}
}
}
}
}
}
}