kar-saaragh's picture
First Push
e092ebd
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8217883110046387,
"min": 0.8113973736763,
"max": 2.872420072555542,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7927.7919921875,
"min": 7927.7919921875,
"max": 29416.453125,
"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": 12.70944595336914,
"min": 0.37071216106414795,
"max": 12.769372940063477,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2478.342041015625,
"min": 71.91815948486328,
"max": 2604.9521484375,
"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": 0.075437201516858,
"min": 0.06368929396381182,
"max": 0.075437201516858,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.301748806067432,
"min": 0.25675240106533703,
"max": 0.36978127881336736,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20320487898938797,
"min": 0.12447571883197217,
"max": 0.2745116896489087,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8128195159575519,
"min": 0.4979028753278887,
"max": 1.3725584482445436,
"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": 25.136363636363637,
"min": 3.272727272727273,
"max": 25.545454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1106.0,
"min": 144.0,
"max": 1405.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.136363636363637,
"min": 3.272727272727273,
"max": 25.545454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1106.0,
"min": 144.0,
"max": 1405.0,
"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": "1704534045",
"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": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1704534500"
},
"total": 454.41697344299973,
"count": 1,
"self": 0.8964280669997606,
"children": {
"run_training.setup": {
"total": 0.05601621999994677,
"count": 1,
"self": 0.05601621999994677
},
"TrainerController.start_learning": {
"total": 453.464529156,
"count": 1,
"self": 0.5531783219448698,
"children": {
"TrainerController._reset_env": {
"total": 1.8610033510003632,
"count": 1,
"self": 1.8610033510003632
},
"TrainerController.advance": {
"total": 450.8904373290552,
"count": 18215,
"self": 0.2713193221061374,
"children": {
"env_step": {
"total": 450.61911800694907,
"count": 18215,
"self": 295.46105938499204,
"children": {
"SubprocessEnvManager._take_step": {
"total": 154.88120585691377,
"count": 18215,
"self": 1.4764622338379922,
"children": {
"TorchPolicy.evaluate": {
"total": 153.40474362307577,
"count": 18215,
"self": 153.40474362307577
}
}
},
"workers": {
"total": 0.27685276504325884,
"count": 18215,
"self": 0.0,
"children": {
"worker_root": {
"total": 452.0893124639906,
"count": 18215,
"is_parallel": true,
"self": 222.33643704703263,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0030170250001901877,
"count": 1,
"is_parallel": true,
"self": 0.0007381070008705137,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002278917999319674,
"count": 10,
"is_parallel": true,
"self": 0.002278917999319674
}
}
},
"UnityEnvironment.step": {
"total": 0.038796488999651046,
"count": 1,
"is_parallel": true,
"self": 0.0006270699986998807,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004083930007254821,
"count": 1,
"is_parallel": true,
"self": 0.0004083930007254821
},
"communicator.exchange": {
"total": 0.03574918100002833,
"count": 1,
"is_parallel": true,
"self": 0.03574918100002833
},
"steps_from_proto": {
"total": 0.0020118450001973542,
"count": 1,
"is_parallel": true,
"self": 0.0004231450002407655,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015886999999565887,
"count": 10,
"is_parallel": true,
"self": 0.0015886999999565887
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 229.75287541695798,
"count": 18214,
"is_parallel": true,
"self": 10.753759285981687,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.549897133969353,
"count": 18214,
"is_parallel": true,
"self": 5.549897133969353
},
"communicator.exchange": {
"total": 178.61068433505352,
"count": 18214,
"is_parallel": true,
"self": 178.61068433505352
},
"steps_from_proto": {
"total": 34.83853466195342,
"count": 18214,
"is_parallel": true,
"self": 6.545170123982643,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.293364537970774,
"count": 182140,
"is_parallel": true,
"self": 28.293364537970774
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00010688899965316523,
"count": 1,
"self": 0.00010688899965316523,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 445.0620172419649,
"count": 689089,
"is_parallel": true,
"self": 14.340789017021052,
"children": {
"process_trajectory": {
"total": 246.47810398994352,
"count": 689089,
"is_parallel": true,
"self": 245.80055867294323,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6775453170002947,
"count": 4,
"is_parallel": true,
"self": 0.6775453170002947
}
}
},
"_update_policy": {
"total": 184.24312423500032,
"count": 90,
"is_parallel": true,
"self": 57.61119612997936,
"children": {
"TorchPPOOptimizer.update": {
"total": 126.63192810502096,
"count": 4587,
"is_parallel": true,
"self": 126.63192810502096
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1598032649999368,
"count": 1,
"self": 0.0014401749995158752,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15836309000042093,
"count": 1,
"self": 0.15836309000042093
}
}
}
}
}
}
}