CAJ | 학술논문

强化学习算法通常要处理连续状态及连续动作空间问题以实现精确控制。就此文中结合Actor-Critic方法在处理连续动作空间的优点及核方法在处理连续状态空间的优势,提出一种基于核方法的连续动作Actor-Critic学习算法( KCACL)。该算法中,Actor根据奖赏不作为原则更新动作概率,Critic采用基于核方法的在线选择时间差分算法学习状态值函数。对比实验验证该算法的有效性。
강화학습산법통상요처리련속상태급련속동작공간문제이실현정학공제。취차문중결합Actor-Critic방법재처리련속동작공간적우점급핵방법재처리련속상태공간적우세,제출일충기우핵방법적련속동작Actor-Critic학습산법( KCACL)。해산법중,Actor근거장상불작위원칙경신동작개솔,Critic채용기우핵방법적재선선택시간차분산법학습상태치함수。대비실험험증해산법적유효성。
In reinforcement learning, the learning algorithms frequently have to deal with both continuous state and continuous action spaces to control accurately. In this paper, the great capacity of kernel method for handling continuous state space problems and the advantage of actor-critic method in dealing with continuous action space problems are combined. Kernel-based continuous-action actor-critic learning ( KCACL ) is proposed grounded on the combination. In KCACL, the actor updates each action probability based on reward-inaction, and the critic updates the state value function according to online selective kernel-based temporal difference( OSKTD) learning. The experimental results demonstrate the effectiveness of the proposed algorithm.