pneubauer's picture
First push
efa4c03
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.22802734375,
"min": 1.22802734375,
"max": 2.882859945297241,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 11725.205078125,
"min": 11725.205078125,
"max": 29523.369140625,
"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": 12.572566032409668,
"min": 0.39757493138313293,
"max": 12.572566032409668,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2451.650390625,
"min": 77.1295394897461,
"max": 2540.89404296875,
"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": 0.06624437915803248,
"min": 0.06343387265185918,
"max": 0.07423849760713946,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26497751663212993,
"min": 0.26398508468592435,
"max": 0.3582269236343992,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21340386814930862,
"min": 0.1028091835857862,
"max": 0.2697678285135942,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8536154725972345,
"min": 0.4112367343431448,
"max": 1.348839142567971,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000009e-06,
"min": 8.082097306000009e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.2328389224000035e-05,
"min": 3.2328389224000035e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.09999999999999998,
"min": 0.09999999999999998,
"max": 0.09999999999999998,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.3999999999999999,
"min": 0.3999999999999999,
"max": 0.4999999999999999,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.004864970599999999,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.34090909090909,
"min": 3.340909090909091,
"max": 25.34090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1115.0,
"min": 147.0,
"max": 1364.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.34090909090909,
"min": 3.340909090909091,
"max": 25.34090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1115.0,
"min": 147.0,
"max": 1364.0,
"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": "1675368915",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1675369445"
},
"total": 530.043132253,
"count": 1,
"self": 0.44107871799997156,
"children": {
"run_training.setup": {
"total": 0.110055836000015,
"count": 1,
"self": 0.110055836000015
},
"TrainerController.start_learning": {
"total": 529.491997699,
"count": 1,
"self": 0.5892431529954365,
"children": {
"TrainerController._reset_env": {
"total": 10.03372921099998,
"count": 1,
"self": 10.03372921099998
},
"TrainerController.advance": {
"total": 518.7114042030043,
"count": 18204,
"self": 0.29306866101251217,
"children": {
"env_step": {
"total": 518.4183355419918,
"count": 18204,
"self": 360.0703692039896,
"children": {
"SubprocessEnvManager._take_step": {
"total": 158.0591777459981,
"count": 18204,
"self": 1.5539053050003417,
"children": {
"TorchPolicy.evaluate": {
"total": 156.50527244099777,
"count": 18204,
"self": 34.22086610899294,
"children": {
"TorchPolicy.sample_actions": {
"total": 122.28440633200483,
"count": 18204,
"self": 122.28440633200483
}
}
}
}
},
"workers": {
"total": 0.2887885920040958,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 528.0866989269947,
"count": 18204,
"is_parallel": true,
"self": 284.162296419989,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0063997889999996005,
"count": 1,
"is_parallel": true,
"self": 0.003828390000080617,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0025713989999189835,
"count": 10,
"is_parallel": true,
"self": 0.0025713989999189835
}
}
},
"UnityEnvironment.step": {
"total": 0.03765141399998129,
"count": 1,
"is_parallel": true,
"self": 0.0003546929999629356,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00030438599998205973,
"count": 1,
"is_parallel": true,
"self": 0.00030438599998205973
},
"communicator.exchange": {
"total": 0.0348447200000237,
"count": 1,
"is_parallel": true,
"self": 0.0348447200000237
},
"steps_from_proto": {
"total": 0.0021476150000125926,
"count": 1,
"is_parallel": true,
"self": 0.0005979570000249623,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015496579999876303,
"count": 10,
"is_parallel": true,
"self": 0.0015496579999876303
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 243.9244025070057,
"count": 18203,
"is_parallel": true,
"self": 9.218141108999248,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.618707934000611,
"count": 18203,
"is_parallel": true,
"self": 5.618707934000611
},
"communicator.exchange": {
"total": 195.15987482400033,
"count": 18203,
"is_parallel": true,
"self": 195.15987482400033
},
"steps_from_proto": {
"total": 33.927678640005524,
"count": 18203,
"is_parallel": true,
"self": 7.5369249749765,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.390753665029024,
"count": 182030,
"is_parallel": true,
"self": 26.390753665029024
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.532700004096114e-05,
"count": 1,
"self": 5.532700004096114e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 515.3815106909831,
"count": 367416,
"is_parallel": true,
"self": 10.126759602019433,
"children": {
"process_trajectory": {
"total": 265.0872204019638,
"count": 367416,
"is_parallel": true,
"self": 264.1672666319638,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9199537700000064,
"count": 4,
"is_parallel": true,
"self": 0.9199537700000064
}
}
},
"_update_policy": {
"total": 240.16753068699984,
"count": 90,
"is_parallel": true,
"self": 71.33840345799376,
"children": {
"TorchPPOOptimizer.update": {
"total": 168.82912722900608,
"count": 7645,
"is_parallel": true,
"self": 168.82912722900608
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15756580500010386,
"count": 1,
"self": 0.0013152080001646027,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15625059699993926,
"count": 1,
"self": 0.15625059699993926
}
}
}
}
}
}
}