Symbolic Generalization for On-line Planning
This work addresses the challenge of costly interactions in on-line planning for Markov decision processes, offering a domain-specific improvement.
The paper tackled the problem of improving on-line planning efficiency by extending Real-Time Dynamic Programming (RTDP) with symbolic generalization, resulting in significant reductions in both computation time and real-world interactions required for convergence.
Symbolic representations have been used successfully in off-line planning algorithms for Markov decision processes. We show that they can also improve the performance of on-line planners. In addition to reducing computation time, symbolic generalization can reduce the amount of costly real-world interactions required for convergence. We introduce Symbolic Real-Time Dynamic Programming (or sRTDP), an extension of RTDP. After each step of on-line interaction with an environment, sRTDP uses symbolic model-checking techniques to generalizes its experience by updating a group of states rather than a single state. We examine two heuristic approaches to dynamic grouping of states and show that they accelerate the planning process significantly in terms of both CPU time and the number of steps of interaction with the environment.