Showing 2026Show all
3 papers · 1 filter
cs.LG2026
Bias-Controlled Primal-Dual Natural Actor-Critic: Optimal Rates for Constrained Multi-Objective Average-Reward RL
Ankur Naskar, Swetha Ganesh, Vaneet Aggarwal
Many reinforcement learning (RL) problems in the infinite-horizon average-reward setting require optimizing multiple conflicting objectives while satisfying multiple safety constra…
cs.LG2026
Adversary-Robust Learning from Fully Asynchronous Directional Derivative Estimates
Anik Kumar Paul, Nibedita Roy, Nagesh Talagani +3
We propose FAR-SIGN (Fully Asynchronous Robust optimization via SIGNed directional projections) for adversary-resilient learning in parameter-server--worker systems. FAR-SIGN achie…
cs.LG2026
Breaking the Bias Barrier in Concave Multi-Objective Reinforcement Learning
Swetha Ganesh, Vaneet Aggarwal
While standard reinforcement learning optimizes a single reward signal, many applications require optimizing a nonlinear utility over multiple objectives, wh…