Co-occurring keywords · papers mentioning both
average-reward markov decision process
(1)
approximate factorization
(1)
graph-coloring-based optimal synchronous sampling
(1)
near-minimax sample complexity
(1)
weakly communicating mdp
(1)
model-free algorithm
(1)
model-based algorithm
(1)
model-free reinforcement learning
(1)
average reward
(1)
regret bound
(1)
Papers
Overcoming the Curse of Dimensionality in Reinforcement Learning Through Approximate Factorization
ICML 2025
Sharper Model-free Reinforcement Learning for Average-reward Markov Decision Processes
COLT 2023