中立報酬関数で敵対的模倣学習の報酬バイアスを解消
Addressing reward bias in Adversarial Imitation Learning with neutral reward functions
GAILの報酬関数に起因する生存バイアスと終了バイアスを理論的に分析し、複数の終端状態を持つタスク環境でも機能する新たな中立報酬関数を提案した論文。
著者: Rohit Jena, Siddharth Agrawal, Katia Sycara
分類: cs.LG, cs.RO, stat.ML
原文アブストラクト
Generative Adversarial Imitation Learning suffers from the fundamental problem of reward bias stemming from the choice of reward functions used in the algorithm. Different types of biases also affect different types of environments - which are broadly divided into survival and task-based environments. We provide a theoretical sketch of why existing reward functions would fail in imitation learning scenarios in task based environments with multiple terminal states. We also propose a new reward function for GAIL which outperforms existing GAIL methods on task based environments with single and multiple terminal states and effectively overcomes both survival and termination bias.
