5 papers
Randomized Least Squares Value Iteration itself is Joint Differentially Private
Haiyang Lu, Pratik Gajane, Shaojie Bai +1
As reinforcement learning (RL) increasingly applies to sensitive domains, such as health care and recommendation systems, privacy-preserving techniques have become essential to pro…
On the Sample Complexity of Discounted Reinforcement Learning with Optimized Certainty Equivalents
Oliver Mortensen, Mohammad Sadegh Talebi
We study risk-sensitive reinforcement learning in finite discounted MDPs, where a generative model of the MDP is assumed to be available. We consider a family or risk measures call…
Recursive Entropic Risk Optimization in Discounted MDPs: Sample Complexity Bounds with a Generative Model
Oliver Mortensen, Mohammad Sadegh Talebi
We study risk-sensitive reinforcement learning in finite discounted MDPs with recursive entropic risk measures (ERM), where the risk parameter controls the agent's risk…
Near-Optimal Reinforcement Learning with Shuffle Differential Privacy
Shaojie Bai, Mohammad Sadegh Talebi, Chengcheng Zhao +2
Reinforcement learning (RL) is a powerful tool for sequential decision-making, but its application is often hindered by privacy concerns arising from its interaction data. This cha…
Provably Efficient Exploration in Reward Machines with Low Regret
Hippolyte Bourel, Anders Jonsson, Odalric-Ambrym Maillard +2
We study reinforcement learning (RL) for decision processes with non-Markovian reward, in which high-level knowledge of the task in the form of reward machines is available to the…