Pumin1's picture
First Push
9883968 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.5289406776428223,
"min": 1.5289406776428223,
"max": 2.883399248123169,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 14463.779296875,
"min": 14463.779296875,
"max": 31083.044921875,
"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": 9.952914237976074,
"min": 0.029140986502170563,
"max": 9.952914237976074,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1005.244384765625,
"min": 2.8266756534576416,
"max": 1005.244384765625,
"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.Environment.CumulativeReward.mean": {
"value": 21.057692307692307,
"min": 2.772727272727273,
"max": 21.057692307692307,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1095.0,
"min": 122.0,
"max": 1095.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 21.057692307692307,
"min": 2.772727272727273,
"max": 21.057692307692307,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1095.0,
"min": 122.0,
"max": 1095.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.050273758308963704,
"min": 0.045043371796697,
"max": 0.0533959577924179,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.10054751661792741,
"min": 0.090086743593394,
"max": 0.1488011910063078,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2866695192368591,
"min": 0.10391156605499632,
"max": 0.3120382786819748,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.5733390384737183,
"min": 0.20782313210999265,
"max": 0.9361148360459244,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 4.200097900000005e-06,
"min": 4.200097900000005e-06,
"max": 0.00019340000329999996,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 8.40019580000001e-06,
"min": 8.40019580000001e-06,
"max": 0.0004944000528,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10105000000000003,
"min": 0.10105000000000003,
"max": 0.14834999999999998,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.20210000000000006,
"min": 0.20210000000000006,
"max": 0.4236,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001147900000000001,
"min": 0.0001147900000000001,
"max": 0.00483533,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0002295800000000002,
"min": 0.0002295800000000002,
"max": 0.01236528,
"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": "1718797367",
"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/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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1718797848"
},
"total": 480.50715524299994,
"count": 1,
"self": 0.4456376040000123,
"children": {
"run_training.setup": {
"total": 0.057098257000006924,
"count": 1,
"self": 0.057098257000006924
},
"TrainerController.start_learning": {
"total": 480.0044193819999,
"count": 1,
"self": 0.6503906970127673,
"children": {
"TrainerController._reset_env": {
"total": 2.954757344999848,
"count": 1,
"self": 2.954757344999848
},
"TrainerController.advance": {
"total": 476.30040994698743,
"count": 18210,
"self": 0.31345094897437775,
"children": {
"env_step": {
"total": 475.98695899801305,
"count": 18210,
"self": 296.0224547870132,
"children": {
"SubprocessEnvManager._take_step": {
"total": 179.64838219498756,
"count": 18210,
"self": 1.5978953409776295,
"children": {
"TorchPolicy.evaluate": {
"total": 178.05048685400993,
"count": 18210,
"self": 178.05048685400993
}
}
},
"workers": {
"total": 0.3161220160122866,
"count": 18210,
"self": 0.0,
"children": {
"worker_root": {
"total": 478.62274917099194,
"count": 18210,
"is_parallel": true,
"self": 235.40069872197728,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00533288300005097,
"count": 1,
"is_parallel": true,
"self": 0.0035872359999302716,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001745647000120698,
"count": 10,
"is_parallel": true,
"self": 0.001745647000120698
}
}
},
"UnityEnvironment.step": {
"total": 0.041851452999935645,
"count": 1,
"is_parallel": true,
"self": 0.0007525180001266563,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044787000001633714,
"count": 1,
"is_parallel": true,
"self": 0.00044787000001633714
},
"communicator.exchange": {
"total": 0.03854719499986459,
"count": 1,
"is_parallel": true,
"self": 0.03854719499986459
},
"steps_from_proto": {
"total": 0.0021038699999280652,
"count": 1,
"is_parallel": true,
"self": 0.0004235110000081477,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016803589999199176,
"count": 10,
"is_parallel": true,
"self": 0.0016803589999199176
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 243.22205044901466,
"count": 18209,
"is_parallel": true,
"self": 10.679853488974686,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.796239777019309,
"count": 18209,
"is_parallel": true,
"self": 5.796239777019309
},
"communicator.exchange": {
"total": 190.9655965590075,
"count": 18209,
"is_parallel": true,
"self": 190.9655965590075
},
"steps_from_proto": {
"total": 35.780360624013156,
"count": 18209,
"is_parallel": true,
"self": 6.965563021003618,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.814797603009538,
"count": 182090,
"is_parallel": true,
"self": 28.814797603009538
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016804599999886705,
"count": 1,
"self": 0.00016804599999886705,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 470.74988085199743,
"count": 681351,
"is_parallel": true,
"self": 14.871372762904457,
"children": {
"process_trajectory": {
"total": 246.92047255809348,
"count": 681351,
"is_parallel": true,
"self": 245.69639004509327,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2240825130002122,
"count": 4,
"is_parallel": true,
"self": 1.2240825130002122
}
}
},
"_update_policy": {
"total": 208.9580355309995,
"count": 45,
"is_parallel": true,
"self": 81.22006490799481,
"children": {
"TorchPPOOptimizer.update": {
"total": 127.73797062300468,
"count": 3060,
"is_parallel": true,
"self": 127.73797062300468
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.0986933469998803,
"count": 1,
"self": 0.001148833999877752,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09754451300000255,
"count": 1,
"self": 0.09754451300000255
}
}
}
}
}
}
}