ニューラル報酬関数によるオープンエンド強化学習
Open-Ended Reinforcement Learning with Neural Reward Functions
ニューラルネットワークで表現した報酬関数を反復的に訓練し、多様で複雑なスキルを自律的に獲得する強化学習手法を提案した論文。
著者: Robert Meier, Asier Mujika
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
Inspired by the great success of unsupervised learning in Computer Vision and Natural Language Processing, the Reinforcement Learning community has recently started to focus more on unsupervised discovery of skills. Most current approaches, like DIAYN or DADS, optimize some form of mutual information objective. We propose a different approach that uses reward functions encoded by neural networks. These are trained iteratively to reward more complex behavior. In high-dimensional robotic environments our approach learns a wide range of interesting skills including front-flips for Half-Cheetah and one-legged running for Humanoid. In the pixel-based Montezuma's Revenge environment our method also works with minimal changes and it learns complex skills that involve interacting with items and visiting diverse locations. The implementation of our approach can be found in this link: https://github.com/amujika/Open-Ended-Reinforcement-Learning-with-Neural-Reward-Functions.
