Sutton’s Dyna framework provides a novel and computationally appealing way to integrate learning, planning, and reacting in autonomous agents. Examined here is a class of strategies designed to enhance the learning and planning power of Dyna systems by increasing their computational efficiency. The benefit of using these strategies is demonstrated on some simple abstract learning tasks.
All Science Journal Classification (ASJC) codes
- Experimental and Cognitive Psychology
- Behavioral Neuroscience
- dynamic programming
- reinforcement learning
- sequential decision problems