Reinforcement learning promises a generic method for adapting agents to arbitrary tasks in arbitrary stochastic environments, but applying it to new real-world problems remains di...
In this paper, we consider Markov Decision Processes (MDPs) with error states. Error states are those states entering which is undesirable or dangerous. We define the risk with re...
Reinforcement learning in real-world domains suffers from three curses of dimensionality: explosions in state and action spaces, and high stochasticity. We present approaches that ...
Closed-loop control relies on sensory feedback that is usually assumed to be free. But if sensing incurs a cost, it may be coste ective to take sequences of actions in open-loop m...
Eric A. Hansen, Andrew G. Barto, Shlomo Zilberstei...
Reinforcement learning (RL) can be impractical for many high dimensional problems because of the computational cost of doing stochastic search in large state spaces. We propose a ...