We present a general methodology to automate the search for equilibrium strategies in games derived from computational experimentation. Our approach interleaves empirical game-the...
We present a new subgoal-based method for automatically creating useful skills in reinforcement learning. Our method identifies subgoals by partitioning local state transition gra...
It is known that the complexity of the reinforcement learning algorithms, such as Q-learning, may be exponential in the number of environment’s states. It was shown, however, th...
R-max is a very simple model-based reinforcement learning algorithm which can attain near-optimal average reward in polynomial time. In R-max, the agent always maintains a complet...
Abstract. We investigate the problem of using function approximation in reinforcement learning where the agent’s policy is represented as a classifier mapping states to actions....