We investigate a general semi-Markov Decision Process (SMDP) framework for modeling concurrent decision making, where agents learn optimal plans over concurrent temporally extended actions. We introduce three types of parallel termination schemes - all, any and continue - and theoretically and experimentally compare them.

We investigate a general semi-Markov Decision Process (SMDP) framework for modeling concurrent decision making, where agents learn optimal plans over concurrent temporally extended actions. We introduce three types of parallel termination schemes - all, any and continue - and theoretically and experimentally compare them.

Learning to Take Concurrent ActionsKhashayar Rohanimanesh Department of Computer Science University of Massachusetts Amherst, MA 01003 khash@cs.umass.edu Abstract We investigate a general semi-Markov Decision Process (SMDP) framework for modeling concurrent decision making, where agents learn optimal plans over concurrent temporally extended actions. We introduce three types of parallel termination schemes - all, any and continue - and theoretically and experimentally compare them. 1 Introduction We investigate a general framework for modeling concurrent actions. The notion of concurrent action is formalized in a general way, to capture both situations where a single agent can execute multiple parallel processes, as well as the multi-agent case where many agents act in parallel. Concurrency clearly allows agents to achieve goals more quickly: in making breakfast, we interleave making toast and coffee with other activities such as getting milk; in driving, we search for road signs while controlling the wheel, accelerator and brakes.