nakato-nk's picture
First Push
9c91630 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9548003673553467,
"min": 0.9548003673553467,
"max": 2.8538942337036133,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9074.4228515625,
"min": 9074.4228515625,
"max": 29132.552734375,
"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": 12.428600311279297,
"min": 0.30778422951698303,
"max": 12.428600311279297,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2423.5771484375,
"min": 59.710140228271484,
"max": 2503.16015625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07375691396237907,
"min": 0.06518793585921372,
"max": 0.07375691396237907,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2950276558495163,
"min": 0.26075174343685487,
"max": 0.35102524360049486,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1670305646736832,
"min": 0.09538782154798836,
"max": 0.28541397347169767,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6681222586947329,
"min": 0.38155128619195344,
"max": 1.4270698673584883,
"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": 24.59090909090909,
"min": 3.0454545454545454,
"max": 24.59090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1082.0,
"min": 134.0,
"max": 1328.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.59090909090909,
"min": 3.0454545454545454,
"max": 24.59090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1082.0,
"min": 134.0,
"max": 1328.0,
"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": "1742859951",
"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": "1742860402"
},
"total": 451.46429825399997,
"count": 1,
"self": 0.48605957899997065,
"children": {
"run_training.setup": {
"total": 0.023323512999979812,
"count": 1,
"self": 0.023323512999979812
},
"TrainerController.start_learning": {
"total": 450.954915162,
"count": 1,
"self": 0.40554422400236945,
"children": {
"TrainerController._reset_env": {
"total": 3.1895951070000024,
"count": 1,
"self": 3.1895951070000024
},
"TrainerController.advance": {
"total": 447.25382073199756,
"count": 18192,
"self": 0.3985159090075854,
"children": {
"env_step": {
"total": 320.9421581679908,
"count": 18192,
"self": 244.80076947699519,
"children": {
"SubprocessEnvManager._take_step": {
"total": 75.91635119699163,
"count": 18192,
"self": 1.3903719149897142,
"children": {
"TorchPolicy.evaluate": {
"total": 74.52597928200191,
"count": 18192,
"self": 74.52597928200191
}
}
},
"workers": {
"total": 0.22503749400397055,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 449.2702226319939,
"count": 18192,
"is_parallel": true,
"self": 234.52913493799252,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00526997700001175,
"count": 1,
"is_parallel": true,
"self": 0.0036005850000719875,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016693919999397622,
"count": 10,
"is_parallel": true,
"self": 0.0016693919999397622
}
}
},
"UnityEnvironment.step": {
"total": 0.08407612999997127,
"count": 1,
"is_parallel": true,
"self": 0.0006302339999706419,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004192719999878136,
"count": 1,
"is_parallel": true,
"self": 0.0004192719999878136
},
"communicator.exchange": {
"total": 0.07885287400000607,
"count": 1,
"is_parallel": true,
"self": 0.07885287400000607
},
"steps_from_proto": {
"total": 0.0041737500000067485,
"count": 1,
"is_parallel": true,
"self": 0.002550970000072539,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016227799999342096,
"count": 10,
"is_parallel": true,
"self": 0.0016227799999342096
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 214.74108769400135,
"count": 18191,
"is_parallel": true,
"self": 10.049697768995827,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.687691511006335,
"count": 18191,
"is_parallel": true,
"self": 5.687691511006335
},
"communicator.exchange": {
"total": 165.21639448399753,
"count": 18191,
"is_parallel": true,
"self": 165.21639448399753
},
"steps_from_proto": {
"total": 33.787303930001656,
"count": 18191,
"is_parallel": true,
"self": 6.211901848990578,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.575402081011077,
"count": 181910,
"is_parallel": true,
"self": 27.575402081011077
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 125.9131466549992,
"count": 18192,
"self": 0.4899043760081554,
"children": {
"process_trajectory": {
"total": 28.480580562990838,
"count": 18192,
"self": 27.9239527139909,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5566278489999377,
"count": 4,
"self": 0.5566278489999377
}
}
},
"_update_policy": {
"total": 96.9426617160002,
"count": 90,
"self": 38.835610200000644,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.10705151599956,
"count": 4587,
"self": 58.10705151599956
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4040000451132073e-06,
"count": 1,
"self": 1.4040000451132073e-06
},
"TrainerController._save_models": {
"total": 0.10595369500003926,
"count": 1,
"self": 0.0009702950001155841,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10498339999992368,
"count": 1,
"self": 0.10498339999992368
}
}
}
}
}
}
}