QUOTA: The Quantile Option Architecture for Reinforcement Learning

By Shangtong Zhang, Borislav Mavrin, Linglong Kong, Bo Liu, Hengshuai Yao. 2018

33 citations recorded by the source corpus.

In this paper, we propose the Quantile Option Architecture (QUOTA) for exploration based on recent advances in distributional reinforcement learning (RL). In QUOTA, decision making is based on quantiles of a value distribution, not only the mean. QUOTA provides a new dimension for exploration via making use of both optimism and pessimism of a value distribution. We demonstrate the performance advantage of QUOTA in both challenging video games and physical robot simulators.

Subfields: Artificial Intelligence, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Hengshuai Yao
2. Shangtong Zhang
3. Linglong Kong
4. Yaoliang Yu
5. Kaiwen Wu
6. Borislav Mavrin
7. Wouter M. Kouw

In Management Science and Operations Research

1. Shangtong Zhang
2. Linglong Kong
3. Yaoliang Yu
4. Hengshuai Yao
5. Borislav Mavrin

Citations in the corpus

• Distributional Reinforcement Learning for Efficient Exploration (2019, background): “Zhang et al. (2019) generated risk-seeking and risk-averse policies via distributional RL for exploration, making use of both optimism and pessimism of intrinsic uncertainty.”