ztchir's picture
First Push
31b2ba7 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8551608324050903,
"min": 0.8551608324050903,
"max": 2.863596200942993,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8165.07568359375,
"min": 8165.07568359375,
"max": 29326.087890625,
"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": 12.908926963806152,
"min": 0.34415456652641296,
"max": 12.908926963806152,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2517.24072265625,
"min": 66.76598358154297,
"max": 2609.585205078125,
"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": 0.06376970518841499,
"min": 0.061386327852754705,
"max": 0.07624879626660808,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25507882075365995,
"min": 0.24554531141101882,
"max": 0.36629197873316666,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1981519541027499,
"min": 0.11478586280010822,
"max": 0.27956054391814217,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7926078164109996,
"min": 0.4591434512004329,
"max": 1.3978027195907108,
"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": 3.2954545454545454,
"max": 25.436363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1112.0,
"min": 145.0,
"max": 1399.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.272727272727273,
"min": 3.2954545454545454,
"max": 25.436363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1112.0,
"min": 145.0,
"max": 1399.0,
"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": "1720549044",
"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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1720549507"
},
"total": 463.87291561000006,
"count": 1,
"self": 0.6577600130000292,
"children": {
"run_training.setup": {
"total": 0.05525936300000467,
"count": 1,
"self": 0.05525936300000467
},
"TrainerController.start_learning": {
"total": 463.15989623400003,
"count": 1,
"self": 0.591940387005593,
"children": {
"TrainerController._reset_env": {
"total": 2.2275597830000606,
"count": 1,
"self": 2.2275597830000606
},
"TrainerController.advance": {
"total": 460.19576808799457,
"count": 18201,
"self": 0.27721076700152025,
"children": {
"env_step": {
"total": 459.91855732099305,
"count": 18201,
"self": 298.7527347889735,
"children": {
"SubprocessEnvManager._take_step": {
"total": 160.871258721005,
"count": 18201,
"self": 1.5264102020114478,
"children": {
"TorchPolicy.evaluate": {
"total": 159.34484851899356,
"count": 18201,
"self": 159.34484851899356
}
}
},
"workers": {
"total": 0.294563811014541,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 461.90253251699903,
"count": 18201,
"is_parallel": true,
"self": 232.57437778398844,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0033642420000887796,
"count": 1,
"is_parallel": true,
"self": 0.0008879160001242781,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0024763259999645015,
"count": 10,
"is_parallel": true,
"self": 0.0024763259999645015
}
}
},
"UnityEnvironment.step": {
"total": 0.0678634810000176,
"count": 1,
"is_parallel": true,
"self": 0.0006678050001482916,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004337629999326964,
"count": 1,
"is_parallel": true,
"self": 0.0004337629999326964
},
"communicator.exchange": {
"total": 0.06455843199989886,
"count": 1,
"is_parallel": true,
"self": 0.06455843199989886
},
"steps_from_proto": {
"total": 0.0022034810000377547,
"count": 1,
"is_parallel": true,
"self": 0.00046058200018705975,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001742898999850695,
"count": 10,
"is_parallel": true,
"self": 0.001742898999850695
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 229.3281547330106,
"count": 18200,
"is_parallel": true,
"self": 10.380060784023271,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.5578206519980995,
"count": 18200,
"is_parallel": true,
"self": 5.5578206519980995
},
"communicator.exchange": {
"total": 178.67443159098661,
"count": 18200,
"is_parallel": true,
"self": 178.67443159098661
},
"steps_from_proto": {
"total": 34.71584170600261,
"count": 18200,
"is_parallel": true,
"self": 6.561069892036471,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.154771813966136,
"count": 182000,
"is_parallel": true,
"self": 28.154771813966136
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00010808799993355933,
"count": 1,
"self": 0.00010808799993355933,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 454.42512175699574,
"count": 690549,
"is_parallel": true,
"self": 14.508595830963486,
"children": {
"process_trajectory": {
"total": 251.96563543203285,
"count": 690549,
"is_parallel": true,
"self": 251.1412543010331,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8243811309997682,
"count": 4,
"is_parallel": true,
"self": 0.8243811309997682
}
}
},
"_update_policy": {
"total": 187.9508904939994,
"count": 90,
"is_parallel": true,
"self": 57.741633900997385,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.209256593002,
"count": 4587,
"is_parallel": true,
"self": 130.209256593002
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14451988799987703,
"count": 1,
"self": 0.004861969999865323,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1396579180000117,
"count": 1,
"self": 0.1396579180000117
}
}
}
}
}
}
}