logo
today local_bar
average-reward MDP

2 papers across 1 session

Poster Session 6

2 papers
Friday, December 5, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
Regret Analysis of Average-Reward Unichain MDPs via an Actor-Critic Approach
#3201 · Swetha Ganesh, Vaneet Aggarwal
Finite-Time Bounds for Average-Reward Fitted Q-Iteration
#208 · Jongmin Lee, Ernest Ryu

We characterize sample complexities for average-reward offline RL with function approximation for weakly communicating MDPs.