We propose a modular reinforcement learning architecture for non-linear, nonstationary control tasks, which we call multiple model-based reinforcement learning (MMRL). The basic i...
Compositional Q-Learning (CQ-L) (Singh 1992) is a modular approach to learning to performcomposite tasks made up of several elemental tasks by reinforcement learning. Skills acqui...
A new training algorithm is presented for delayed reinforcement learning problems that does not assume the existence of a critic model and employs the polytope optimization algorit...
Human experience with interactive games will be enhanced if the software agents that play the game learn from their failures. Techniques such as reinforcement learning provide one...
1 Reinforcement learning has become a widely used methodology for creating intelligent agents in a wide range of applications. However, its performance deteriorates in tasks with s...