qbbian's picture
First Push
d0d1486 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.043882131576538,
"min": 1.043882131576538,
"max": 2.8664498329162598,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9978.46875,
"min": 9978.46875,
"max": 29481.4375,
"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": 13.044361114501953,
"min": 0.20171280205249786,
"max": 13.08988094329834,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2543.650390625,
"min": 39.13228225708008,
"max": 2667.71142578125,
"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": 0.06819054163576106,
"min": 0.061604747021862985,
"max": 0.07654751247276842,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27276216654304425,
"min": 0.25949995310557095,
"max": 0.36622377549978335,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19108149544427208,
"min": 0.09157213522806107,
"max": 0.28433811384088853,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7643259817770883,
"min": 0.3662885409122443,
"max": 1.4216905692044426,
"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": 25.272727272727273,
"min": 2.6136363636363638,
"max": 26.045454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1112.0,
"min": 115.0,
"max": 1426.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.272727272727273,
"min": 2.6136363636363638,
"max": 26.045454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1112.0,
"min": 115.0,
"max": 1426.0,
"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": "1734148476",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.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": "1734149034"
},
"total": 558.779089318,
"count": 1,
"self": 0.5424986060000947,
"children": {
"run_training.setup": {
"total": 0.07537382399999615,
"count": 1,
"self": 0.07537382399999615
},
"TrainerController.start_learning": {
"total": 558.1612168879999,
"count": 1,
"self": 0.788843284005111,
"children": {
"TrainerController._reset_env": {
"total": 7.029925248999973,
"count": 1,
"self": 7.029925248999973
},
"TrainerController.advance": {
"total": 550.2571964299947,
"count": 18203,
"self": 0.3874533479940965,
"children": {
"env_step": {
"total": 549.8697430820006,
"count": 18203,
"self": 425.3820293429903,
"children": {
"SubprocessEnvManager._take_step": {
"total": 124.09728431600848,
"count": 18203,
"self": 1.8969714620038758,
"children": {
"TorchPolicy.evaluate": {
"total": 122.20031285400461,
"count": 18203,
"self": 122.20031285400461
}
}
},
"workers": {
"total": 0.3904294230018195,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 556.5993144640051,
"count": 18203,
"is_parallel": true,
"self": 264.0348345200011,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0033349529999782135,
"count": 1,
"is_parallel": true,
"self": 0.0007779999999115716,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002556953000066642,
"count": 10,
"is_parallel": true,
"self": 0.002556953000066642
}
}
},
"UnityEnvironment.step": {
"total": 0.04442461899998307,
"count": 1,
"is_parallel": true,
"self": 0.0007864839999456308,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00045518899997887274,
"count": 1,
"is_parallel": true,
"self": 0.00045518899997887274
},
"communicator.exchange": {
"total": 0.04084834400003956,
"count": 1,
"is_parallel": true,
"self": 0.04084834400003956
},
"steps_from_proto": {
"total": 0.0023346020000190038,
"count": 1,
"is_parallel": true,
"self": 0.00045501100004230466,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001879590999976699,
"count": 10,
"is_parallel": true,
"self": 0.001879590999976699
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 292.56447994400406,
"count": 18202,
"is_parallel": true,
"self": 13.569669611002666,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.909767177004142,
"count": 18202,
"is_parallel": true,
"self": 6.909767177004142
},
"communicator.exchange": {
"total": 230.03436211899867,
"count": 18202,
"is_parallel": true,
"self": 230.03436211899867
},
"steps_from_proto": {
"total": 42.05068103699858,
"count": 18202,
"is_parallel": true,
"self": 8.142434765030544,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.90824627196804,
"count": 182020,
"is_parallel": true,
"self": 33.90824627196804
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00021644399998876906,
"count": 1,
"self": 0.00021644399998876906,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 544.0385490329774,
"count": 727248,
"is_parallel": true,
"self": 15.46491326002149,
"children": {
"process_trajectory": {
"total": 294.0572085409559,
"count": 727248,
"is_parallel": true,
"self": 293.276093619956,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7811149209999257,
"count": 4,
"is_parallel": true,
"self": 0.7811149209999257
}
}
},
"_update_policy": {
"total": 234.516427232,
"count": 90,
"is_parallel": true,
"self": 68.93811486399557,
"children": {
"TorchPPOOptimizer.update": {
"total": 165.57831236800445,
"count": 4581,
"is_parallel": true,
"self": 165.57831236800445
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08503548100009084,
"count": 1,
"self": 0.0011241670000572412,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0839113140000336,
"count": 1,
"self": 0.0839113140000336
}
}
}
}
}
}
}