Effective handling of dialogue state in the hidden information state POMDP-based dialogue manager

Effective dialogue management is critically dependent on the information that is encoded in the dialogue state. In order to deploy reinforcement learning for policy optimization, dialogue must be modeled as a Markov Decision Process. This requires that the dialogue statemust encode all relevent information obtained during the dialogue prior to that state. This can be achieved by combining the user goal, the dialogue history, and the last user action to form the dialogue state. In addition, to gain robustness to input errors, dialogue must be modeled as a Partially Observable Markov Decision Process (POMDP) and hence, a distribution over all possible states must be maintained at every dialogue turn. This poses a potential computational limitation since there can be a very large number of dialogue states. The Hidden Information State model provides a principled way of ensuring tractability in a POMDP-based dialogue model. The key feature of this model is the grouping of user goals into partitions that are dynamically built during the dialogue. In this article, we extend this model further to incorporate the notion of complements. This allows for a more complex user goal to be represented, and it enables an effective pruning technique to be implemented that preserves the overall system performance within a limited computational resource more effectively than existing approaches. © 2011 ACM.

Experimental studies of an accelerating, pitching, flat plate at low Reynolds number

The understanding of low Reynolds number aerodynamics is becoming increasingly prevalent with the recent surge in interest in advanced Micro-Air Vehicle (MAV) technology. Research in this area has been primarily stimulated by a military need for smaller, more versatile, autonomous, surveillance aircraft. The mechanism for providing the high lift coefficient required forMAV applications is thought to be largely influenced by the formation of a Leading Edge Vortex (LEV). This paper analyses experimentally, the influence of the LEV effect for a flat plate wing (AR = 4) under fast and slow pitch-up motions at Re =10,000 using a combination of dye flow visualisation and PIV measurements. It is found that a fast pitch over 1c shows a flow topology dominant LEV, while for a slow pitch case over 6c, the flow is largely separated. The development of the suction surface flow and the LEV was strongly correlated with the kinematics of the leading edge, suggesting that the effective local angle of incidence at the Leading Edge (LE) is of considerable significance in unsteady pitching motions. © 2013 by P.R.R.J Stevens.