A Review of Uncertainty for Deep Reinforcement Learning


  • Owen Lockwood Rensselaer Polytechnic Institute
  • Mei Si Rensselaer Polytechnic Institute




Reinforcement Learning, Uncertainty, Deep Learning, Exploration


Uncertainty is ubiquitous in games, both in the agents playing games and often in the games themselves. Working with uncertainty is therefore an important component of successful deep reinforcement learning agents. While there has been substantial effort and progress in understanding and working with uncertainty for supervised learning, the body of literature for uncertainty aware deep reinforcement learning is less developed. While many of the same problems regarding uncertainty in neural networks for supervised learning remain for reinforcement learning, there are additional sources of uncertainty due to the nature of an interactable environment. In this work, we provide an overview motivating and presenting existing techniques in uncertainty aware deep reinforcement learning. These works show empirical benefits on a variety of reinforcement learning tasks. This work serves to help to centralize the disparate results and promote future research in this area.




How to Cite

Lockwood, O., & Si, M. (2022). A Review of Uncertainty for Deep Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, 18(1), 155-162. https://doi.org/10.1609/aiide.v18i1.21959