This paper investigates the impact of reward shaping on a reinforcement learning-based spoken dialogue system’s learning. A diffuse reward function gives a reward after each transition between two dialogue states. A sparse function only gives a reward at the end of the dialogue. Reward shaping consists of learning a diffuse function without modifying the optimal policy compared to a sparse one....

We extend the method of controlled Lagrangians to include potential shaping for complete state-space stabilization of mechanical systems. The method of controlled Lagrangians deals with mechanical systems with symmetry and provides symmetry-preserving kinetic shaping and feedback-controlled dissipation for state-space stabilization in all but the symmetry variables. Potential shaping complement...