暂无分享,去创建一个
Relational representations in reinforcement learning allow for the use of structural information like the presence of objects and relationships between them in the description of value functions. Through this paper, we show that such representations allow for the inclusion of background knowledge that qualitatively describes a state and fan be used to design agents that demonstrate learning behavior in domains with large state and actions spaces such as computer games.
[1] John E. Laird,et al. Soar-RL: integrating reinforcement learning with Soar , 2005, Cognitive Systems Research.
[2] Allen Newell,et al. Toward real-time GOMS , 1993 .
[3] Andre Cohen,et al. An object-oriented representation for efficient reinforcement learning , 2008, ICML '08.
[4] Mahesan Niranjan,et al. On-line Q-learning using connectionist systems , 1994 .
[5] John E. Laird,et al. Extending the Soar Cognitive Architecture , 2008, AGI.