In sequential decision-making problems formulated as Markov decision processes, state-value function approximation using domain features is a critical technique for scaling up the...
Abstract. Recently, there has been increasing interests in applying aspect models (e.g., PLSA and LDA) in image segmentation. However, these models ignore spatial relationships amo...
In this paper, we present a new entertainment adaptive framework AIRSF for stress free air travels. Based on the passenger's current and target comfort states, user entertain...
Future agent applications will increasingly represent human users autonomously or semi-autonomously in strategic interactions with similar entities. Hence, there is a growing need...
The goal of Reinforcement learning (RL) is to maximize reward (minimize cost) in a Markov decision process (MDP) without knowing the underlying model a priori. RL algorithms tend ...