PhiTau's picture
First Push
08ad589 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7568385004997253,
"min": 0.7568385004997253,
"max": 2.8350071907043457,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7192.9931640625,
"min": 7192.9931640625,
"max": 28939.75390625,
"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": 12.919838905334473,
"min": 0.3958960473537445,
"max": 12.958074569702148,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2519.36865234375,
"min": 76.8038330078125,
"max": 2643.447265625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07098433667481147,
"min": 0.06263529035227383,
"max": 0.07535649592019206,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28393734669924586,
"min": 0.2505411614090953,
"max": 0.36018033586046666,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18544372653259952,
"min": 0.12877229589959788,
"max": 0.26979603177192163,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7417749061303981,
"min": 0.5150891835983915,
"max": 1.3489801588596082,
"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": 25.15909090909091,
"min": 3.8181818181818183,
"max": 25.613636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1107.0,
"min": 168.0,
"max": 1383.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.15909090909091,
"min": 3.8181818181818183,
"max": 25.613636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1107.0,
"min": 168.0,
"max": 1383.0,
"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": "1744096239",
"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": "1744096667"
},
"total": 428.08787420399995,
"count": 1,
"self": 0.43756525100002364,
"children": {
"run_training.setup": {
"total": 0.02681328999995003,
"count": 1,
"self": 0.02681328999995003
},
"TrainerController.start_learning": {
"total": 427.62349566299997,
"count": 1,
"self": 0.3483345530016777,
"children": {
"TrainerController._reset_env": {
"total": 3.23714290800001,
"count": 1,
"self": 3.23714290800001
},
"TrainerController.advance": {
"total": 423.9500362409981,
"count": 18192,
"self": 0.37019339099310855,
"children": {
"env_step": {
"total": 300.66137217500636,
"count": 18192,
"self": 228.4983136530085,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.95647378699789,
"count": 18192,
"self": 1.2589203839864922,
"children": {
"TorchPolicy.evaluate": {
"total": 70.6975534030114,
"count": 18192,
"self": 70.6975534030114
}
}
},
"workers": {
"total": 0.20658473499997854,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 426.099319137993,
"count": 18192,
"is_parallel": true,
"self": 225.64813562900338,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.009308412999985194,
"count": 1,
"is_parallel": true,
"self": 0.007826456000202597,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014819569997825965,
"count": 10,
"is_parallel": true,
"self": 0.0014819569997825965
}
}
},
"UnityEnvironment.step": {
"total": 0.03582619500002693,
"count": 1,
"is_parallel": true,
"self": 0.000573291000023346,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004092849999324244,
"count": 1,
"is_parallel": true,
"self": 0.0004092849999324244
},
"communicator.exchange": {
"total": 0.03270006700006434,
"count": 1,
"is_parallel": true,
"self": 0.03270006700006434
},
"steps_from_proto": {
"total": 0.002143552000006821,
"count": 1,
"is_parallel": true,
"self": 0.0003791019997834155,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017644500002234054,
"count": 10,
"is_parallel": true,
"self": 0.0017644500002234054
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 200.45118350898963,
"count": 18191,
"is_parallel": true,
"self": 9.65561898897613,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.343307948001097,
"count": 18191,
"is_parallel": true,
"self": 5.343307948001097
},
"communicator.exchange": {
"total": 154.0347870980089,
"count": 18191,
"is_parallel": true,
"self": 154.0347870980089
},
"steps_from_proto": {
"total": 31.417469474003497,
"count": 18191,
"is_parallel": true,
"self": 5.6324093209429975,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.7850601530605,
"count": 181910,
"is_parallel": true,
"self": 25.7850601530605
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 122.91847067499862,
"count": 18192,
"self": 0.44425533199910205,
"children": {
"process_trajectory": {
"total": 26.805057398000827,
"count": 18192,
"self": 26.254612360001147,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5504450379996797,
"count": 4,
"self": 0.5504450379996797
}
}
},
"_update_policy": {
"total": 95.66915794499869,
"count": 90,
"self": 38.42531106299862,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.24384688200007,
"count": 4587,
"self": 57.24384688200007
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.590000900061568e-07,
"count": 1,
"self": 9.590000900061568e-07
},
"TrainerController._save_models": {
"total": 0.08798100200010595,
"count": 1,
"self": 0.0008943890002228727,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08708661299988307,
"count": 1,
"self": 0.08708661299988307
}
}
}
}
}
}
}