Timezone: »

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

Tue Jun 11 05:00 PM -- 05:05 PM (PDT) @ Room 104

One of the main challenges in reinforcement learning is on solving tasks with sparse reward. We first show that the difficulty of discovering the rewarding state is bounded by the expected cover time of the underlying random walk induced by a policy. We propose a method to discover options automatically which reduce the cover time so as to speed up the exploration in sparse reward domains. We show empirically that the proposed algorithm successfully reduces the cover time, and improves the performance of the reinforcement learning agents.

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