acblue's picture
First Push
890b60f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8277919888496399,
"min": 0.8277547955513,
"max": 2.8712565898895264,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8450.1005859375,
"min": 7939.82421875,
"max": 29309.787109375,
"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": 4.29077672958374,
"min": 0.31552404165267944,
"max": 4.355674743652344,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 836.7014770507812,
"min": 60.58061599731445,
"max": 888.5576171875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0693463364230268,
"min": 0.06469077863335305,
"max": 0.07356309917568248,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2773853456921072,
"min": 0.2587631145334122,
"max": 0.36704627149818264,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.16505869927213473,
"min": 0.0985764165331299,
"max": 0.21109246374929652,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6602347970885389,
"min": 0.3943056661325196,
"max": 0.9788764119148254,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 7.890097370000006e-06,
"min": 7.890097370000006e-06,
"max": 0.00029169000276999994,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.1560389480000026e-05,
"min": 3.1560389480000026e-05,
"max": 0.0013842000385999999,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10263000000000001,
"min": 0.10263000000000001,
"max": 0.19723000000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41052000000000005,
"min": 0.41052000000000005,
"max": 0.9614,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00014123700000000008,
"min": 0.00014123700000000008,
"max": 0.004861776999999999,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005649480000000003,
"min": 0.0005649480000000003,
"max": 0.023073859999999995,
"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": 25.0,
"min": 3.4318181818181817,
"max": 25.527272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1100.0,
"min": 151.0,
"max": 1404.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.0,
"min": 3.4318181818181817,
"max": 25.527272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1100.0,
"min": 151.0,
"max": 1404.0,
"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": "1733341435",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn --resume ./ml-agents/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": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1733341873"
},
"total": 437.99645615400004,
"count": 1,
"self": 0.39147809399992184,
"children": {
"run_training.setup": {
"total": 0.0674715400000423,
"count": 1,
"self": 0.0674715400000423
},
"TrainerController.start_learning": {
"total": 437.5375065200001,
"count": 1,
"self": 0.35635906803781836,
"children": {
"TrainerController._reset_env": {
"total": 2.0669090910000705,
"count": 1,
"self": 2.0669090910000705
},
"TrainerController.advance": {
"total": 435.027342140962,
"count": 18192,
"self": 0.3621815499454897,
"children": {
"env_step": {
"total": 307.13186036700336,
"count": 18192,
"self": 233.35074481803758,
"children": {
"SubprocessEnvManager._take_step": {
"total": 73.56203923299654,
"count": 18192,
"self": 1.2821836470302514,
"children": {
"TorchPolicy.evaluate": {
"total": 72.27985558596629,
"count": 18192,
"self": 72.27985558596629
}
}
},
"workers": {
"total": 0.21907631596923238,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 436.2005918790278,
"count": 18192,
"is_parallel": true,
"self": 231.80332731300177,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0021426050002446573,
"count": 1,
"is_parallel": true,
"self": 0.0006750170005034306,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014675879997412267,
"count": 10,
"is_parallel": true,
"self": 0.0014675879997412267
}
}
},
"UnityEnvironment.step": {
"total": 0.0812143200000719,
"count": 1,
"is_parallel": true,
"self": 0.0006550210000568768,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040514800002711127,
"count": 1,
"is_parallel": true,
"self": 0.00040514800002711127
},
"communicator.exchange": {
"total": 0.07806328200013013,
"count": 1,
"is_parallel": true,
"self": 0.07806328200013013
},
"steps_from_proto": {
"total": 0.0020908689998577756,
"count": 1,
"is_parallel": true,
"self": 0.00038336600073307636,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017075029991246993,
"count": 10,
"is_parallel": true,
"self": 0.0017075029991246993
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 204.39726456602602,
"count": 18191,
"is_parallel": true,
"self": 10.016303909009366,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.449955834039429,
"count": 18191,
"is_parallel": true,
"self": 5.449955834039429
},
"communicator.exchange": {
"total": 155.5601601059907,
"count": 18191,
"is_parallel": true,
"self": 155.5601601059907
},
"steps_from_proto": {
"total": 33.37084471698654,
"count": 18191,
"is_parallel": true,
"self": 6.063213151920536,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.307631565066004,
"count": 181910,
"is_parallel": true,
"self": 27.307631565066004
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 127.53330022401315,
"count": 18192,
"self": 0.42967916102179515,
"children": {
"process_trajectory": {
"total": 28.887163765989953,
"count": 18192,
"self": 28.4983937069901,
"children": {
"RLTrainer._checkpoint": {
"total": 0.38877005899985306,
"count": 4,
"self": 0.38877005899985306
}
}
},
"_update_policy": {
"total": 98.2164572970014,
"count": 90,
"self": 39.23939108801051,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.97706620899089,
"count": 4587,
"self": 58.97706620899089
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0250000741507392e-06,
"count": 1,
"self": 1.0250000741507392e-06
},
"TrainerController._save_models": {
"total": 0.08689519500012466,
"count": 1,
"self": 0.000848307000069326,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08604688800005533,
"count": 1,
"self": 0.08604688800005533
}
}
}
}
}
}
}