`

( events)   Timezone: »  
Poster
Wed Dec 09 09:00 AM -- 11:00 AM (PST) @ Poster Session 3 #1073
Towards Safe Policy Improvement for Non-Stationary MDPs
Yash Chandak · Scott Jordan · Georgios Theocharous · Martha White · Philip Thomas

Many real-world sequential decision-making problems involve critical systems with financial risks and human-life risks. While several works in the past have proposed methods that are safe for deployment, they assume that the underlying problem is stationary. However, many real-world problems of interest exhibit non-stationarity, and when stakes are high, the cost associated with a false stationarity assumption may be unacceptable. We take the first steps towards ensuring safety, with high confidence, for smoothly-varying non-stationary decision problems. Our proposed method extends a type of safe algorithm, called a Seldonian algorithm, through a synthesis of model-free reinforcement learning with time-series analysis. Safety is ensured using sequential hypothesis testing of a policy’s forecasted performance, and confidence intervals are obtained using wild bootstrap.