Devyaansh123's picture
First Push
0e73bdc verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.961303174495697,
"min": 0.944362223148346,
"max": 2.8636605739593506,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9136.2255859375,
"min": 9066.283203125,
"max": 29232.24609375,
"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": 13.02010440826416,
"min": 0.5240764617919922,
"max": 13.024601936340332,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2538.92041015625,
"min": 101.67083740234375,
"max": 2651.693603515625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06982935958270294,
"min": 0.06205648586511219,
"max": 0.07386742867189848,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27931743833081174,
"min": 0.24822594346044877,
"max": 0.3640707644443347,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19342695578348404,
"min": 0.11596179459650326,
"max": 0.27140308076552316,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7737078231339362,
"min": 0.463847178386013,
"max": 1.3170192381914922,
"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.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": 25.045454545454547,
"min": 3.340909090909091,
"max": 26.036363636363635,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1102.0,
"min": 147.0,
"max": 1432.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.045454545454547,
"min": 3.340909090909091,
"max": 26.036363636363635,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1102.0,
"min": 147.0,
"max": 1432.0,
"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": "1752307857",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1752308377"
},
"total": 519.649118838,
"count": 1,
"self": 0.5427614590000758,
"children": {
"run_training.setup": {
"total": 0.03781420699988303,
"count": 1,
"self": 0.03781420699988303
},
"TrainerController.start_learning": {
"total": 519.0685431720001,
"count": 1,
"self": 0.5796616449849807,
"children": {
"TrainerController._reset_env": {
"total": 4.101622814000166,
"count": 1,
"self": 4.101622814000166
},
"TrainerController.advance": {
"total": 514.3142614410151,
"count": 18192,
"self": 0.6169854020397452,
"children": {
"env_step": {
"total": 364.9615427719864,
"count": 18192,
"self": 313.53443482401303,
"children": {
"SubprocessEnvManager._take_step": {
"total": 51.06756233898409,
"count": 18192,
"self": 1.7544937469767774,
"children": {
"TorchPolicy.evaluate": {
"total": 49.31306859200731,
"count": 18192,
"self": 49.31306859200731
}
}
},
"workers": {
"total": 0.359545608989265,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 517.0029015729965,
"count": 18192,
"is_parallel": true,
"self": 245.4396442170189,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007491086999834806,
"count": 1,
"is_parallel": true,
"self": 0.004808147999938228,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002682938999896578,
"count": 10,
"is_parallel": true,
"self": 0.002682938999896578
}
}
},
"UnityEnvironment.step": {
"total": 0.08132423600000038,
"count": 1,
"is_parallel": true,
"self": 0.0006495799998447183,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003988270000263583,
"count": 1,
"is_parallel": true,
"self": 0.0003988270000263583
},
"communicator.exchange": {
"total": 0.07799278800007414,
"count": 1,
"is_parallel": true,
"self": 0.07799278800007414
},
"steps_from_proto": {
"total": 0.0022830410000551637,
"count": 1,
"is_parallel": true,
"self": 0.00039216099980876606,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018908800002463977,
"count": 10,
"is_parallel": true,
"self": 0.0018908800002463977
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 271.5632573559776,
"count": 18191,
"is_parallel": true,
"self": 12.895703109947362,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.106414924018054,
"count": 18191,
"is_parallel": true,
"self": 7.106414924018054
},
"communicator.exchange": {
"total": 212.09505115800357,
"count": 18191,
"is_parallel": true,
"self": 212.09505115800357
},
"steps_from_proto": {
"total": 39.466088164008625,
"count": 18191,
"is_parallel": true,
"self": 7.4998007319725275,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.966287432036097,
"count": 181910,
"is_parallel": true,
"self": 31.966287432036097
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 148.73573326698897,
"count": 18192,
"self": 0.7968197010027325,
"children": {
"process_trajectory": {
"total": 28.40696496798546,
"count": 18192,
"self": 28.045917886985762,
"children": {
"RLTrainer._checkpoint": {
"total": 0.36104708099969685,
"count": 4,
"self": 0.36104708099969685
}
}
},
"_update_policy": {
"total": 119.53194859800078,
"count": 90,
"self": 46.745206854996695,
"children": {
"TorchPPOOptimizer.update": {
"total": 72.78674174300409,
"count": 4587,
"self": 72.78674174300409
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0159999419556698e-06,
"count": 1,
"self": 1.0159999419556698e-06
},
"TrainerController._save_models": {
"total": 0.07299625599989668,
"count": 1,
"self": 0.0013930449999861594,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07160321099991052,
"count": 1,
"self": 0.07160321099991052
}
}
}
}
}
}
}