A Multi-agent Reinforcement Learning with Weighted Experience Sharing

作者：Yu Lasheng^*; Abdulai Issahaku

来源：7th International Conference on Intelligent Computing (ICIC), 2011-08-11 to 2011-08-14.

• Reinforcement Learning
• Q-Learning
• Multi-agent Reinforcement Learning
• Weighted Experience

Reinforcement Learning, also sometimes called learning by rewards and punishments is the problem faced by an agent that must learn behavior through trial-and-error interactions with a dynamic environment [1]. With repeated trials however, it is expected that the agent learns to perfect its behavior overtime. In this paper we simulate the reinforcement learning process of a mobile agent on a grid space and examine the situation in which multiple reinforcement learning agents can be used to speed up the learning process by sharing their Q-values. We propose a sharing method which takes into consideration the weight of the experience acquired by each agent on the occasion of visiting a state and taking an action.

• 出版日期2012
• 单位中南大学