Learning Type-Generalized Actions for Symbolic Planning
Daniel Tanneberg,Michael Gienger,Daniel Tanneberg,Michael Gienger
Symbolic planning is a powerful technique to solve complex tasks that require long sequences of actions and can equip an intelligent agent with complex behavior. The downside of this approach is the necessity for suitable symbolic representations describing the state of the environment as well as the actions that can change it. Traditionally such representations are carefully hand-designed by expe...
