MathgeniusTB's picture
First Push
fbbee2c verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7413401007652283,
"min": 0.7413401007652283,
"max": 2.840670585632324,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7045.6962890625,
"min": 7045.6962890625,
"max": 28997.56640625,
"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": 13.016356468200684,
"min": 0.41015419363975525,
"max": 13.016356468200684,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2538.189453125,
"min": 79.56991577148438,
"max": 2651.98583984375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0729714437032931,
"min": 0.06267432114976805,
"max": 0.07301323520444689,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2918857748131724,
"min": 0.2506972845990722,
"max": 0.361947113996875,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1828616804205904,
"min": 0.13831833919268283,
"max": 0.29142621685476866,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7314467216823616,
"min": 0.5532733567707313,
"max": 1.4571310842738432,
"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": 26.068181818181817,
"min": 3.909090909090909,
"max": 26.068181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1147.0,
"min": 172.0,
"max": 1424.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.068181818181817,
"min": 3.909090909090909,
"max": 26.068181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1147.0,
"min": 172.0,
"max": 1424.0,
"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": "1769823369",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1769823815"
},
"total": 445.936610178,
"count": 1,
"self": 0.4303898040001286,
"children": {
"run_training.setup": {
"total": 0.027195267999900352,
"count": 1,
"self": 0.027195267999900352
},
"TrainerController.start_learning": {
"total": 445.479025106,
"count": 1,
"self": 0.3936058080088287,
"children": {
"TrainerController._reset_env": {
"total": 3.5903852939999297,
"count": 1,
"self": 3.5903852939999297
},
"TrainerController.advance": {
"total": 441.4165046449913,
"count": 18192,
"self": 0.4243206499799044,
"children": {
"env_step": {
"total": 319.23613455798977,
"count": 18192,
"self": 249.35004428998195,
"children": {
"SubprocessEnvManager._take_step": {
"total": 69.6623568980068,
"count": 18192,
"self": 1.2755776520149311,
"children": {
"TorchPolicy.evaluate": {
"total": 68.38677924599187,
"count": 18192,
"self": 68.38677924599187
}
}
},
"workers": {
"total": 0.223733370001014,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 443.67745017001516,
"count": 18192,
"is_parallel": true,
"self": 225.2274657180102,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0030624629999920217,
"count": 1,
"is_parallel": true,
"self": 0.0016404200000579294,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014220429999340922,
"count": 10,
"is_parallel": true,
"self": 0.0014220429999340922
}
}
},
"UnityEnvironment.step": {
"total": 0.08718965100001697,
"count": 1,
"is_parallel": true,
"self": 0.0007056560000364698,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039747000005263544,
"count": 1,
"is_parallel": true,
"self": 0.00039747000005263544
},
"communicator.exchange": {
"total": 0.08374076299992339,
"count": 1,
"is_parallel": true,
"self": 0.08374076299992339
},
"steps_from_proto": {
"total": 0.00234576200000447,
"count": 1,
"is_parallel": true,
"self": 0.0005107650001718866,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018349969998325832,
"count": 10,
"is_parallel": true,
"self": 0.0018349969998325832
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 218.44998445200497,
"count": 18191,
"is_parallel": true,
"self": 10.233902805991988,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.492097247999027,
"count": 18191,
"is_parallel": true,
"self": 5.492097247999027
},
"communicator.exchange": {
"total": 167.0099157319986,
"count": 18191,
"is_parallel": true,
"self": 167.0099157319986
},
"steps_from_proto": {
"total": 35.71406866601535,
"count": 18191,
"is_parallel": true,
"self": 6.610164898067978,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.103903767947372,
"count": 181910,
"is_parallel": true,
"self": 29.103903767947372
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 121.7560494370216,
"count": 18192,
"self": 0.507588295037749,
"children": {
"process_trajectory": {
"total": 26.374324224984434,
"count": 18192,
"self": 25.829347574984354,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5449766500000806,
"count": 4,
"self": 0.5449766500000806
}
}
},
"_update_policy": {
"total": 94.87413691699942,
"count": 90,
"self": 38.863843381986385,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.010293535013034,
"count": 4587,
"self": 56.010293535013034
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.290001005661907e-07,
"count": 1,
"self": 8.290001005661907e-07
},
"TrainerController._save_models": {
"total": 0.07852852999985771,
"count": 1,
"self": 0.000748187999761285,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07778034200009643,
"count": 1,
"self": 0.07778034200009643
}
}
}
}
}
}
}