matansol's picture
First Push
c40533b
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9051588177680969,
"min": 0.8963233232498169,
"max": 2.883120059967041,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8732.0673828125,
"min": 8548.2353515625,
"max": 29684.603515625,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.634817123413086,
"min": 0.1687285304069519,
"max": 13.659710884094238,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2795.137451171875,
"min": 32.733333587646484,
"max": 2795.542724609375,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.654545454545456,
"min": 2.8636363636363638,
"max": 26.945454545454545,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1466.0,
"min": 126.0,
"max": 1482.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.654545454545456,
"min": 2.8636363636363638,
"max": 26.945454545454545,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1466.0,
"min": 126.0,
"max": 1482.0,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.05264570182828488,
"min": 0.04062655684766451,
"max": 0.05486133890586001,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.10529140365656976,
"min": 0.08125311369532902,
"max": 0.16007599902799236,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18620147395367714,
"min": 0.09770984310136341,
"max": 0.3029663629975973,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.3724029479073543,
"min": 0.19541968620272682,
"max": 0.8252236653192371,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.0528989824000053e-06,
"min": 3.0528989824000053e-06,
"max": 0.00029609280130239995,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 6.105797964800011e-06,
"min": 6.105797964800011e-06,
"max": 0.0008367984210671999,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10101760000000001,
"min": 0.10101760000000001,
"max": 0.1986976,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.20203520000000003,
"min": 0.20203520000000003,
"max": 0.5789328,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 6.077824000000009e-05,
"min": 6.077824000000009e-05,
"max": 0.00493501024,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00012155648000000018,
"min": 0.00012155648000000018,
"max": 0.013948746719999999,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1701767852",
"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": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1701769058"
},
"total": 1206.055766291,
"count": 1,
"self": 0.4403332169999885,
"children": {
"run_training.setup": {
"total": 0.05733836900003553,
"count": 1,
"self": 0.05733836900003553
},
"TrainerController.start_learning": {
"total": 1205.558094705,
"count": 1,
"self": 1.5677078270073252,
"children": {
"TrainerController._reset_env": {
"total": 3.9376793199999156,
"count": 1,
"self": 3.9376793199999156
},
"TrainerController.advance": {
"total": 1199.9680851599926,
"count": 45472,
"self": 0.7810808939748313,
"children": {
"env_step": {
"total": 1199.1870042660178,
"count": 45472,
"self": 827.2012632630112,
"children": {
"SubprocessEnvManager._take_step": {
"total": 371.2172148459953,
"count": 45472,
"self": 3.785855036005728,
"children": {
"TorchPolicy.evaluate": {
"total": 367.43135980998954,
"count": 45472,
"self": 367.43135980998954
}
}
},
"workers": {
"total": 0.7685261570112516,
"count": 45472,
"self": 0.0,
"children": {
"worker_root": {
"total": 1202.0714061039885,
"count": 45472,
"is_parallel": true,
"self": 570.8041278389835,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005900578000023415,
"count": 1,
"is_parallel": true,
"self": 0.004308776000016223,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001591802000007192,
"count": 10,
"is_parallel": true,
"self": 0.001591802000007192
}
}
},
"UnityEnvironment.step": {
"total": 0.037772193000023435,
"count": 1,
"is_parallel": true,
"self": 0.0006806089999145115,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043201100004353066,
"count": 1,
"is_parallel": true,
"self": 0.00043201100004353066
},
"communicator.exchange": {
"total": 0.03452241900004083,
"count": 1,
"is_parallel": true,
"self": 0.03452241900004083
},
"steps_from_proto": {
"total": 0.002137154000024566,
"count": 1,
"is_parallel": true,
"self": 0.0004565630001707177,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016805909998538482,
"count": 10,
"is_parallel": true,
"self": 0.0016805909998538482
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 631.267278265005,
"count": 45471,
"is_parallel": true,
"self": 27.457396558036635,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 14.277256375996785,
"count": 45471,
"is_parallel": true,
"self": 14.277256375996785
},
"communicator.exchange": {
"total": 498.90002814598597,
"count": 45471,
"is_parallel": true,
"self": 498.90002814598597
},
"steps_from_proto": {
"total": 90.63259718498557,
"count": 45471,
"is_parallel": true,
"self": 17.514476983941904,
"children": {
"_process_rank_one_or_two_observation": {
"total": 73.11812020104367,
"count": 454710,
"is_parallel": true,
"self": 73.11812020104367
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001178270001673809,
"count": 1,
"self": 0.0001178270001673809,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 1186.4615020500348,
"count": 1599785,
"is_parallel": true,
"self": 35.41016830809781,
"children": {
"process_trajectory": {
"total": 839.9877160729371,
"count": 1599785,
"is_parallel": true,
"self": 837.8464539749374,
"children": {
"RLTrainer._checkpoint": {
"total": 2.1412620979997428,
"count": 10,
"is_parallel": true,
"self": 2.1412620979997428
}
}
},
"_update_policy": {
"total": 311.06361766899977,
"count": 113,
"is_parallel": true,
"self": 140.94444492900095,
"children": {
"TorchPPOOptimizer.update": {
"total": 170.11917273999882,
"count": 5760,
"is_parallel": true,
"self": 170.11917273999882
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08450457100002495,
"count": 1,
"self": 0.0008586419999119244,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08364592900011303,
"count": 1,
"self": 0.08364592900011303
}
}
}
}
}
}
}