metapat973's picture
First Push
e4b780f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.0870842933654785,
"min": 2.0870842933654785,
"max": 2.890333652496338,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 19835.6484375,
"min": 19835.6484375,
"max": 29520.33203125,
"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": 4.885587692260742,
"min": -0.0072519658133387566,
"max": 4.885587692260742,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 952.6896362304688,
"min": -1.406881332397461,
"max": 965.3583984375,
"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": 12.454545454545455,
"min": 2.6363636363636362,
"max": 12.659090909090908,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 548.0,
"min": 116.0,
"max": 680.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 12.454545454545455,
"min": 2.6363636363636362,
"max": 12.659090909090908,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 548.0,
"min": 116.0,
"max": 680.0,
"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
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.02340428257593885,
"min": 0.018093377887271344,
"max": 0.0312593111069873,
"count": 19
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.02340428257593885,
"min": 0.018093377887271344,
"max": 0.0312593111069873,
"count": 19
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.3152460167805354,
"min": 0.09032549361387888,
"max": 0.3448050777117411,
"count": 19
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.3152460167805354,
"min": 0.09032549361387888,
"max": 0.3448050777117411,
"count": 19
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.9440993520000114e-06,
"min": 1.9440993520000114e-06,
"max": 0.00028363200545599993,
"count": 19
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.9440993520000114e-06,
"min": 1.9440993520000114e-06,
"max": 0.00028363200545599993,
"count": 19
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10064800000000003,
"min": 0.10064800000000003,
"max": 0.19454399999999994,
"count": 19
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.10064800000000003,
"min": 0.10064800000000003,
"max": 0.19454399999999994,
"count": 19
},
"SnowballTarget.Policy.Beta.mean": {
"value": 4.2335200000000204e-05,
"min": 4.2335200000000204e-05,
"max": 0.0047277456,
"count": 19
},
"SnowballTarget.Policy.Beta.sum": {
"value": 4.2335200000000204e-05,
"min": 4.2335200000000204e-05,
"max": 0.0047277456,
"count": 19
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1768904009",
"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": "1768904619"
},
"total": 610.299831194,
"count": 1,
"self": 0.7473255229997449,
"children": {
"run_training.setup": {
"total": 0.03673461300013514,
"count": 1,
"self": 0.03673461300013514
},
"TrainerController.start_learning": {
"total": 609.5157710580002,
"count": 1,
"self": 0.7749548499903085,
"children": {
"TrainerController._reset_env": {
"total": 3.5493250270001226,
"count": 1,
"self": 3.5493250270001226
},
"TrainerController.advance": {
"total": 605.1103869030098,
"count": 18192,
"self": 0.774158699996633,
"children": {
"env_step": {
"total": 466.55203904601603,
"count": 18192,
"self": 400.26221156603356,
"children": {
"SubprocessEnvManager._take_step": {
"total": 65.80016198198541,
"count": 18192,
"self": 2.31547901299723,
"children": {
"TorchPolicy.evaluate": {
"total": 63.48468296898818,
"count": 18192,
"self": 63.48468296898818
}
}
},
"workers": {
"total": 0.48966549799706627,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 606.2318796970103,
"count": 18192,
"is_parallel": true,
"self": 262.6125146950312,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007053379999888421,
"count": 1,
"is_parallel": true,
"self": 0.004307540999661796,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002745839000226624,
"count": 10,
"is_parallel": true,
"self": 0.002745839000226624
}
}
},
"UnityEnvironment.step": {
"total": 0.0435106420000011,
"count": 1,
"is_parallel": true,
"self": 0.0007944899998619803,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004984100000910985,
"count": 1,
"is_parallel": true,
"self": 0.0004984100000910985
},
"communicator.exchange": {
"total": 0.0399291460000768,
"count": 1,
"is_parallel": true,
"self": 0.0399291460000768
},
"steps_from_proto": {
"total": 0.0022885959999712213,
"count": 1,
"is_parallel": true,
"self": 0.00044582200007425854,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018427739998969628,
"count": 10,
"is_parallel": true,
"self": 0.0018427739998969628
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 343.6193650019791,
"count": 18191,
"is_parallel": true,
"self": 16.489355322988786,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 8.303122894996477,
"count": 18191,
"is_parallel": true,
"self": 8.303122894996477
},
"communicator.exchange": {
"total": 267.16939004599703,
"count": 18191,
"is_parallel": true,
"self": 267.16939004599703
},
"steps_from_proto": {
"total": 51.65749673799678,
"count": 18191,
"is_parallel": true,
"self": 9.686395269975037,
"children": {
"_process_rank_one_or_two_observation": {
"total": 41.97110146802174,
"count": 181910,
"is_parallel": true,
"self": 41.97110146802174
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 137.78418915699717,
"count": 18192,
"self": 1.0452180930087707,
"children": {
"process_trajectory": {
"total": 36.46163361298909,
"count": 18192,
"self": 35.92103321698892,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5406003960001726,
"count": 4,
"self": 0.5406003960001726
}
}
},
"_update_policy": {
"total": 100.27733745099931,
"count": 19,
"self": 52.24067193000019,
"children": {
"TorchPPOOptimizer.update": {
"total": 48.03666552099912,
"count": 570,
"self": 48.03666552099912
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.15499983621703e-06,
"count": 1,
"self": 1.15499983621703e-06
},
"TrainerController._save_models": {
"total": 0.08110312300004807,
"count": 1,
"self": 0.001196170999946844,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07990695200010123,
"count": 1,
"self": 0.07990695200010123
}
}
}
}
}
}
}