Timezone: »

Discovering Options for Exploration by Minimizing Cover Time
Yuu Jinnai · Jee Won Park · David Abel · George Konidaris

Tue Jun 11 06:30 PM -- 09:00 PM (PDT) @ Pacific Ballroom #117

One of the main challenges in reinforcement learning is solving tasks with sparse reward. We show that the difficulty of discovering a distant rewarding state in an MDP is bounded by the expected cover time of a random walk over the graph induced by the MDP's transition dynamics. We therefore propose to accelerate exploration by constructing options that minimize cover time. We introduce a new option discovery algorithm that diminishes the expected cover time by connecting the most distant states in the state-space graph with options. We show empirically that the proposed algorithm improves learning in several domains with sparse rewards.

Author Information

Yuu Jinnai (Brown University)
Jee Won Park (Brown University)

I am a senior in Applied Mathematics and research with Professor Konidaris at Brown University. My main interest is to use data to help people and make better decisions.

David Abel (Brown University)
George Konidaris (Brown)

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

More from the Same Authors