partzel's picture
First Push
250f846 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.1421180963516235,
"min": 1.1329169273376465,
"max": 2.879828691482544,
"count": 25
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10955.197265625,
"min": 10955.197265625,
"max": 29904.140625,
"count": 25
},
"SnowballTarget.Step.mean": {
"value": 249968.0,
"min": 9952.0,
"max": 249968.0,
"count": 25
},
"SnowballTarget.Step.sum": {
"value": 249968.0,
"min": 9952.0,
"max": 249968.0,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.810078620910645,
"min": 0.18433061242103577,
"max": 12.810078620910645,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1908.70166015625,
"min": 27.280929565429688,
"max": 1916.487548828125,
"count": 25
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 25
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 25
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.772727272727273,
"min": 3.25,
"max": 25.772727272727273,
"count": 25
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1134.0,
"min": 143.0,
"max": 1416.0,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.772727272727273,
"min": 3.25,
"max": 25.772727272727273,
"count": 25
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1134.0,
"min": 143.0,
"max": 1416.0,
"count": 25
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07090350354109451,
"min": 0.06402847969587253,
"max": 0.0773912613367429,
"count": 25
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.14180700708218902,
"min": 0.12805695939174505,
"max": 0.2230018813179948,
"count": 25
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21668023360418337,
"min": 0.12169648905960367,
"max": 0.2935980224336674,
"count": 25
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.43336046720836674,
"min": 0.24339297811920735,
"max": 0.8807940673010022,
"count": 25
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.1600097680000001e-05,
"min": 1.1600097680000001e-05,
"max": 0.0004868000026399999,
"count": 25
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 2.3200195360000002e-05,
"min": 2.3200195360000002e-05,
"max": 0.00128880004224,
"count": 25
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10231999999999997,
"min": 0.10231999999999997,
"max": 0.19736,
"count": 25
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.20463999999999993,
"min": 0.20463999999999993,
"max": 0.55776,
"count": 25
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.000172168,
"min": 0.000172168,
"max": 0.006815464,
"count": 25
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.000344336,
"min": 0.000344336,
"max": 0.018047424,
"count": 25
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 25
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 25
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1756157623",
"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=SnowballTarget_nocuriosity_emp --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": "1756158157"
},
"total": 533.699400899,
"count": 1,
"self": 0.4432885069995791,
"children": {
"run_training.setup": {
"total": 0.022569133000160946,
"count": 1,
"self": 0.022569133000160946
},
"TrainerController.start_learning": {
"total": 533.2335432590003,
"count": 1,
"self": 0.46520541799918647,
"children": {
"TrainerController._reset_env": {
"total": 1.8440969479997875,
"count": 1,
"self": 1.8440969479997875
},
"TrainerController.advance": {
"total": 530.8450164240012,
"count": 22744,
"self": 0.47770008594443425,
"children": {
"env_step": {
"total": 380.2842085210391,
"count": 22744,
"self": 291.2741662920548,
"children": {
"SubprocessEnvManager._take_step": {
"total": 88.71820381199313,
"count": 22744,
"self": 1.5717487309275384,
"children": {
"TorchPolicy.evaluate": {
"total": 87.1464550810656,
"count": 22744,
"self": 87.1464550810656
}
}
},
"workers": {
"total": 0.29183841699114055,
"count": 22744,
"self": 0.0,
"children": {
"worker_root": {
"total": 531.6714237400356,
"count": 22744,
"is_parallel": true,
"self": 276.2444947450508,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002012717000070552,
"count": 1,
"is_parallel": true,
"self": 0.0006104379995122144,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014022790005583374,
"count": 10,
"is_parallel": true,
"self": 0.0014022790005583374
}
}
},
"UnityEnvironment.step": {
"total": 0.038336489999892365,
"count": 1,
"is_parallel": true,
"self": 0.0006188199999996868,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004377780001050269,
"count": 1,
"is_parallel": true,
"self": 0.0004377780001050269
},
"communicator.exchange": {
"total": 0.03521203699983744,
"count": 1,
"is_parallel": true,
"self": 0.03521203699983744
},
"steps_from_proto": {
"total": 0.002067854999950214,
"count": 1,
"is_parallel": true,
"self": 0.00039770599960320396,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016701490003470099,
"count": 10,
"is_parallel": true,
"self": 0.0016701490003470099
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 255.4269289949848,
"count": 22743,
"is_parallel": true,
"self": 12.147335247943374,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.841720388033082,
"count": 22743,
"is_parallel": true,
"self": 6.841720388033082
},
"communicator.exchange": {
"total": 196.38263730192875,
"count": 22743,
"is_parallel": true,
"self": 196.38263730192875
},
"steps_from_proto": {
"total": 40.05523605707958,
"count": 22743,
"is_parallel": true,
"self": 7.111828846165736,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.94340721091385,
"count": 227430,
"is_parallel": true,
"self": 32.94340721091385
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 150.08310781701766,
"count": 22744,
"self": 0.5490512520032098,
"children": {
"process_trajectory": {
"total": 30.811707147016023,
"count": 22744,
"self": 30.327101302016217,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4846058449998054,
"count": 5,
"self": 0.4846058449998054
}
}
},
"_update_policy": {
"total": 118.72234941799843,
"count": 56,
"self": 48.25640896302639,
"children": {
"TorchPPOOptimizer.update": {
"total": 70.46594045497204,
"count": 5712,
"self": 70.46594045497204
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.770001270226203e-07,
"count": 1,
"self": 9.770001270226203e-07
},
"TrainerController._save_models": {
"total": 0.0792234919999828,
"count": 1,
"self": 0.0006349229997795192,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07858856900020328,
"count": 1,
"self": 0.07858856900020328
}
}
}
}
}
}
}