Timezone: »

 
Poster
Skill Discovery in Continuous Reinforcement Learning Domains using Skill Chaining
George Konidaris · Andrew G Barto

Wed Dec 09 07:00 PM -- 11:59 PM (PST) @ None #None

We introduce skill chaining, a skill discovery method for reinforcement learning agents in continuous domains, that builds chains of skills leading to an end-of-task reward. We demonstrate experimentally that it creates skills that result in performance benefits in a challenging continuous domain.

Author Information

George Konidaris (Duke University)
Andrew G Barto (University of Massachusetts)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors