drbeane's picture
First Push
8708546 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9367144703865051,
"min": 0.9367144703865051,
"max": 2.872596502304077,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8954.0537109375,
"min": 8954.0537109375,
"max": 29418.26171875,
"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": 12.385581970214844,
"min": 0.48881152272224426,
"max": 12.385581970214844,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2415.1884765625,
"min": 94.82943725585938,
"max": 2509.94189453125,
"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.Losses.PolicyLoss.mean": {
"value": 0.06876111019051213,
"min": 0.06540650094069075,
"max": 0.07490389705321386,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27504444076204854,
"min": 0.261626003762763,
"max": 0.3688025777305216,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20806333137785687,
"min": 0.11980571456860714,
"max": 0.27187634515119535,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8322533255114275,
"min": 0.47922285827442856,
"max": 1.3282615662205455,
"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": 24.295454545454547,
"min": 3.272727272727273,
"max": 24.454545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1069.0,
"min": 144.0,
"max": 1345.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.295454545454547,
"min": 3.272727272727273,
"max": 24.454545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1069.0,
"min": 144.0,
"max": 1345.0,
"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": "1724614863",
"python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1724615310"
},
"total": 447.611804914,
"count": 1,
"self": 0.4384193040000355,
"children": {
"run_training.setup": {
"total": 0.05769423499998538,
"count": 1,
"self": 0.05769423499998538
},
"TrainerController.start_learning": {
"total": 447.115691375,
"count": 1,
"self": 0.5822708479977337,
"children": {
"TrainerController._reset_env": {
"total": 2.8278076149999833,
"count": 1,
"self": 2.8278076149999833
},
"TrainerController.advance": {
"total": 443.6140093100023,
"count": 18202,
"self": 0.2904762259930749,
"children": {
"env_step": {
"total": 443.3235330840092,
"count": 18202,
"self": 286.94993338001984,
"children": {
"SubprocessEnvManager._take_step": {
"total": 156.08135298199454,
"count": 18202,
"self": 1.4741533559845266,
"children": {
"TorchPolicy.evaluate": {
"total": 154.60719962601001,
"count": 18202,
"self": 154.60719962601001
}
}
},
"workers": {
"total": 0.29224672199484303,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 445.92158829900075,
"count": 18202,
"is_parallel": true,
"self": 225.64620074699917,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00541891900002156,
"count": 1,
"is_parallel": true,
"self": 0.003646131000323294,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017727879996982665,
"count": 10,
"is_parallel": true,
"self": 0.0017727879996982665
}
}
},
"UnityEnvironment.step": {
"total": 0.042275070999949094,
"count": 1,
"is_parallel": true,
"self": 0.001472942999953375,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038182399998731853,
"count": 1,
"is_parallel": true,
"self": 0.00038182399998731853
},
"communicator.exchange": {
"total": 0.036615030999996634,
"count": 1,
"is_parallel": true,
"self": 0.036615030999996634
},
"steps_from_proto": {
"total": 0.0038052730000117663,
"count": 1,
"is_parallel": true,
"self": 0.00047053900016180705,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0033347339998499592,
"count": 10,
"is_parallel": true,
"self": 0.0033347339998499592
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 220.27538755200158,
"count": 18201,
"is_parallel": true,
"self": 10.145179401981977,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.168413545012982,
"count": 18201,
"is_parallel": true,
"self": 5.168413545012982
},
"communicator.exchange": {
"total": 172.46137754100403,
"count": 18201,
"is_parallel": true,
"self": 172.46137754100403
},
"steps_from_proto": {
"total": 32.50041706400259,
"count": 18201,
"is_parallel": true,
"self": 6.098264408973023,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.402152655029568,
"count": 182010,
"is_parallel": true,
"self": 26.402152655029568
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012552500004403555,
"count": 1,
"self": 0.00012552500004403555,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 438.33023034803205,
"count": 666049,
"is_parallel": true,
"self": 13.37101604598638,
"children": {
"process_trajectory": {
"total": 241.31427720504644,
"count": 666049,
"is_parallel": true,
"self": 240.32742078204637,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9868564230000629,
"count": 4,
"is_parallel": true,
"self": 0.9868564230000629
}
}
},
"_update_policy": {
"total": 183.64493709699923,
"count": 90,
"is_parallel": true,
"self": 57.37221924099924,
"children": {
"TorchPPOOptimizer.update": {
"total": 126.27271785599999,
"count": 4584,
"is_parallel": true,
"self": 126.27271785599999
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09147807699991972,
"count": 1,
"self": 0.0009370839999292002,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09054099299999052,
"count": 1,
"self": 0.09054099299999052
}
}
}
}
}
}
}