Coarticulation: an approach for generating concurrent plans in Markov decision processes

We study an approach for performing concurrent activities in Markov decision processes (MDPs) based on the coarticulation framework. We assume that the agent has multiple degrees of freedom (DOF) in the action space which enables it to perform activities simultaneously. We demonstrate that one natural way for generating concurrency in the system is by coarticulating among the set of learned activities available to the agent. In general due to the multiple DOF in the system, often there exists a redundant set of admissible sub-optimal policies associated with each learned activity. Such flexibility enables the agent to concurrently commit to several subgoals according to their priority levels, given a new task defined in terms of a set of prioritized subgoals . We present efficient approximate algorithms for computing such policies and for generating concurrent plans. We also evaluate our approach in a simulated domain.

• Type: Conference
• Year: 2005
• Where: ICML
• Authors: Khashayar Rohanimanesh, Sridhar Mahadevan
• Keywords: Admissible Sub-optimal Policies, Efficient Approximate Algorithms, ICML 2005, Machine Learning, Multiple Dof