Improved Regret Bound for Safe Reinforcement Learning via

Tighter Cost Pessimism and Reward Optimism

Aligning Model Properties via Conformal Risk Control

Higher-Order Causal Message Passing for Experimentation with

Complex Interference

Beating Price of Anarchy and Gradient Descent without

Regret in Potential Games

Occupancy Prediction with Patient Data: Evaluating Time-Series,

Patient-Level Aggregation, and Deep Set Models

Global Convergence of Multi-Agent Policy Gradient in

Markov Potential Games

Independent Natural Policy Gradient Always Converges in

Markov Potential Games

Some Ordered Ramsey Numbers of Graphs on Four Vertices