ahmedafifi123's picture
First Push
837627e verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7705751061439514,
"min": 0.7705751061439514,
"max": 2.851062297821045,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7323.5458984375,
"min": 7323.5458984375,
"max": 29103.64453125,
"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": 11.795963287353516,
"min": 0.25453296303749084,
"max": 11.795963287353516,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2300.212890625,
"min": 49.37939453125,
"max": 2389.348388671875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06801023021334379,
"min": 0.06326955653887982,
"max": 0.07611310262571208,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27204092085337517,
"min": 0.2559229162006351,
"max": 0.3651222870234336,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19113470088033113,
"min": 0.11783395766956256,
"max": 0.2890346354859717,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7645388035213245,
"min": 0.47133583067825024,
"max": 1.3177051935710162,
"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": 23.113636363636363,
"min": 3.2954545454545454,
"max": 23.490909090909092,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1017.0,
"min": 145.0,
"max": 1292.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.113636363636363,
"min": 3.2954545454545454,
"max": 23.490909090909092,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1017.0,
"min": 145.0,
"max": 1292.0,
"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": "1738942251",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1738942812"
},
"total": 560.4550002659998,
"count": 1,
"self": 0.5459378980001475,
"children": {
"run_training.setup": {
"total": 0.04009097199991629,
"count": 1,
"self": 0.04009097199991629
},
"TrainerController.start_learning": {
"total": 559.8689713959998,
"count": 1,
"self": 0.5965694340275149,
"children": {
"TrainerController._reset_env": {
"total": 4.0611930669999765,
"count": 1,
"self": 4.0611930669999765
},
"TrainerController.advance": {
"total": 555.1257372279722,
"count": 18192,
"self": 0.6881967189765419,
"children": {
"env_step": {
"total": 389.6405680039679,
"count": 18192,
"self": 333.0087032010433,
"children": {
"SubprocessEnvManager._take_step": {
"total": 56.23934502397651,
"count": 18192,
"self": 1.9779996629658854,
"children": {
"TorchPolicy.evaluate": {
"total": 54.261345361010626,
"count": 18192,
"self": 54.261345361010626
}
}
},
"workers": {
"total": 0.392519778948099,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 557.9321056010126,
"count": 18192,
"is_parallel": true,
"self": 270.38977536802054,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007293423000191979,
"count": 1,
"is_parallel": true,
"self": 0.004433370000242576,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002860052999949403,
"count": 10,
"is_parallel": true,
"self": 0.002860052999949403
}
}
},
"UnityEnvironment.step": {
"total": 0.048968778000016755,
"count": 1,
"is_parallel": true,
"self": 0.000735682000140514,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004970840000169119,
"count": 1,
"is_parallel": true,
"self": 0.0004970840000169119
},
"communicator.exchange": {
"total": 0.045352598999897964,
"count": 1,
"is_parallel": true,
"self": 0.045352598999897964
},
"steps_from_proto": {
"total": 0.002383412999961365,
"count": 1,
"is_parallel": true,
"self": 0.00045430299951476627,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019291100004465989,
"count": 10,
"is_parallel": true,
"self": 0.0019291100004465989
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 287.5423302329921,
"count": 18191,
"is_parallel": true,
"self": 13.988447917975918,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.495366703033824,
"count": 18191,
"is_parallel": true,
"self": 7.495366703033824
},
"communicator.exchange": {
"total": 225.10352853200266,
"count": 18191,
"is_parallel": true,
"self": 225.10352853200266
},
"steps_from_proto": {
"total": 40.954987079979674,
"count": 18191,
"is_parallel": true,
"self": 7.882661311904712,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.07232576807496,
"count": 181910,
"is_parallel": true,
"self": 33.07232576807496
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 164.79697250502772,
"count": 18192,
"self": 0.8353718100406695,
"children": {
"process_trajectory": {
"total": 31.406430528985766,
"count": 18192,
"self": 30.88240066398589,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5240298649998749,
"count": 4,
"self": 0.5240298649998749
}
}
},
"_update_policy": {
"total": 132.5551701660013,
"count": 90,
"self": 50.00233866799863,
"children": {
"TorchPPOOptimizer.update": {
"total": 82.55283149800266,
"count": 4587,
"self": 82.55283149800266
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.73000169324223e-07,
"count": 1,
"self": 9.73000169324223e-07
},
"TrainerController._save_models": {
"total": 0.08547069399992324,
"count": 1,
"self": 0.0014968129999033408,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0839738810000199,
"count": 1,
"self": 0.0839738810000199
}
}
}
}
}
}
}