Sootla, Aivar; Cowen-Rivers, Alexander I; Jafferjee, Taher; Wang, Ziyan; Mguni, David; Wang, Jun; Bou-Ammar, Haitham; (2022) Sauté RL: Almost Surely Safe Reinforcement Learning Using State Augmentation. In: Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan, (eds.) Volume 162: International Conference on Machine Learning, 17-23 July 2022, Baltimore, Maryland, USA. (pp. pp. 20423-20443). Journal of Machine Learning Research: Baltimore, MA, USA.

Preview

Text sootla22a.pdf - Published Version Download (3MB) | Preview

Abstract

Satisfying safety constraints almost surely (or with probability one) can be critical for the deployment of Reinforcement Learning (RL) in real-life applications. For example, plane landing and take-off should ideally occur with probability one. We address the problem by introducing Safety Augmented (Saute) Markov Decision Processes (MDPs), where the safety constraints are eliminated by augmenting them into the state-space and reshaping the objective. We show that Saute MDP satisfies the Bellman equation and moves us closer to solving Safe RL with constraints satisfied almost surely. We argue that Saute MDP allows viewing the Safe RL problem from a different perspective enabling new features. For instance, our approach has a plug-and-play nature, i.e., any RL algorithm can be "Sauteed”. Additionally, state augmentation allows for policy generalization across safety constraints. We finally show that Saute RL algorithms can outperform their state-of-the-art counterparts when constraint satisfaction is of high importance.

Download activity - last month

Export as JSONCSVXML

Download activity - last 12 months

Export as JSONCSVXML

Downloads by country - last 12 months

Export as CSVJSONXML

Archive Staff Only

View Item