AISpace2 Main Tools News Downloads Prototype Tools Customizable Applets Practice Exercises Help About AIspace

What is the major difference between policies generated by SARSA and Q-learning? SARSA tries to avoid s2 while Q-learning does not. SARSA is expected to be more cautious than Q-learning when exploring near dangerous regions like s2.

Main Tools: Graph Searching | Consistency for CSP | SLS for CSP | Deduction | Belief and Decision Networks | Decision Trees | Neural Networks | STRIPS to CSP