An Adaptive Approach for Planning in Dynamic Environments

Planning in a dynamic environment is a complex task that requires several issues to be investigated in order to manage the associated search complexity. In this paper, an adaptive behavior that integrates planning with learning is presented. The former is performed adopting a hierarchical approach, interleaved with execution. The latter, devised to identify new abstract operators, adopts a chunking technique on successful plans. Integration between planning and learning is also promoted by an agent architecture explicitly designed for supporting abstraction.