We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...
Hierarchical reinforcement learning (RL) is a general framework which studies how to exploit the structure of actions and tasks to accelerate policy learning in large domains. Pri...
Reinforcement learning deals with learning optimal or near optimal policies while interacting with the environment. Application domains with many continuous variables are difficul...
: This paper presents a coarse coding technique and an action selection scheme for reinforcement learning (RL) in multi-dimensional and continuous state-action spaces following con...
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...