arjoca's picture
First Push
153e91a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8703618049621582,
"min": 0.8703618049621582,
"max": 2.868659019470215,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8300.640625,
"min": 8300.640625,
"max": 29377.9375,
"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": 12.533366203308105,
"min": 0.45717501640319824,
"max": 12.533366203308105,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2444.00634765625,
"min": 88.69195556640625,
"max": 2538.955810546875,
"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": 0.06393964946790434,
"min": 0.06277064147755429,
"max": 0.07547436539606162,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25575859787161737,
"min": 0.25108256591021716,
"max": 0.3773718269803081,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2002470098143699,
"min": 0.14581437514610954,
"max": 0.2972869533388054,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8009880392574796,
"min": 0.5832575005844381,
"max": 1.4063019755424238,
"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": 25.09090909090909,
"min": 4.181818181818182,
"max": 25.09090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1104.0,
"min": 184.0,
"max": 1352.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.09090909090909,
"min": 4.181818181818182,
"max": 25.09090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1104.0,
"min": 184.0,
"max": 1352.0,
"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": "1707755517",
"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": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1707755941"
},
"total": 424.356401604,
"count": 1,
"self": 0.4401290410000911,
"children": {
"run_training.setup": {
"total": 0.05192435999992995,
"count": 1,
"self": 0.05192435999992995
},
"TrainerController.start_learning": {
"total": 423.86434820299996,
"count": 1,
"self": 0.5331460469990361,
"children": {
"TrainerController._reset_env": {
"total": 3.513349111000025,
"count": 1,
"self": 3.513349111000025
},
"TrainerController.advance": {
"total": 419.72086899100077,
"count": 18198,
"self": 0.25484017900851086,
"children": {
"env_step": {
"total": 419.46602881199226,
"count": 18198,
"self": 268.77320347599004,
"children": {
"SubprocessEnvManager._take_step": {
"total": 150.4167585529981,
"count": 18198,
"self": 1.4018599539936076,
"children": {
"TorchPolicy.evaluate": {
"total": 149.01489859900448,
"count": 18198,
"self": 149.01489859900448
}
}
},
"workers": {
"total": 0.2760667830041257,
"count": 18198,
"self": 0.0,
"children": {
"worker_root": {
"total": 422.75876025899356,
"count": 18198,
"is_parallel": true,
"self": 210.50669626700028,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005630039000038778,
"count": 1,
"is_parallel": true,
"self": 0.004200922000336504,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014291169997022735,
"count": 10,
"is_parallel": true,
"self": 0.0014291169997022735
}
}
},
"UnityEnvironment.step": {
"total": 0.0718245199999501,
"count": 1,
"is_parallel": true,
"self": 0.0007378050000852454,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000372509999920112,
"count": 1,
"is_parallel": true,
"self": 0.000372509999920112
},
"communicator.exchange": {
"total": 0.0687978869999597,
"count": 1,
"is_parallel": true,
"self": 0.0687978869999597
},
"steps_from_proto": {
"total": 0.00191631799998504,
"count": 1,
"is_parallel": true,
"self": 0.0003909980001708391,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015253199998142009,
"count": 10,
"is_parallel": true,
"self": 0.0015253199998142009
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 212.25206399199328,
"count": 18197,
"is_parallel": true,
"self": 10.213883986996052,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.170213510003464,
"count": 18197,
"is_parallel": true,
"self": 5.170213510003464
},
"communicator.exchange": {
"total": 164.575666992999,
"count": 18197,
"is_parallel": true,
"self": 164.575666992999
},
"steps_from_proto": {
"total": 32.29229950199476,
"count": 18197,
"is_parallel": true,
"self": 6.009164200980308,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.283135301014454,
"count": 181970,
"is_parallel": true,
"self": 26.283135301014454
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011904400003004412,
"count": 1,
"self": 0.00011904400003004412,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 414.35769617909125,
"count": 664454,
"is_parallel": true,
"self": 13.358859918127791,
"children": {
"process_trajectory": {
"total": 229.94204985596343,
"count": 664454,
"is_parallel": true,
"self": 229.46502402296323,
"children": {
"RLTrainer._checkpoint": {
"total": 0.47702583300019796,
"count": 4,
"is_parallel": true,
"self": 0.47702583300019796
}
}
},
"_update_policy": {
"total": 171.05678640500003,
"count": 90,
"is_parallel": true,
"self": 48.39145817900339,
"children": {
"TorchPPOOptimizer.update": {
"total": 122.66532822599663,
"count": 4587,
"is_parallel": true,
"self": 122.66532822599663
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09686501000010139,
"count": 1,
"self": 0.0009624690001146519,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09590254099998674,
"count": 1,
"self": 0.09590254099998674
}
}
}
}
}
}
}