Towards Global Optimality for Practical Average Reward Reinforcement Learning without Mixing Time Oraclesby Bhrij Patel,…
Unveil Conditional Diffusion Models with Classifier-free Guidance: A Sharp Statistical Theoryby Hengyu Fu, Zhuoran Yang,…
The Value of Reward Lookahead in Reinforcement Learningby Nadav Merlis, Dorian Baudry, Vianney PerchetFirst submitted…
Offline Multitask Representation Learning for Reinforcement Learningby Haque Ishfaq, Thanh Nguyen-Tang, Songtao Feng, Raman Arora,…
Variational Sampling of Temporal Trajectoriesby Jurijs Nazarovs, Zhichun Huang, Xingjian Zhen, Sourav Pal, Rudrasis Chakraborty,…
State-Separated SARSA: A Practical Sequential Decision-Making Algorithm with Recovering Rewardsby Yuto Tanimoto, Kenji FukumizuFirst submitted…
Prior-dependent analysis of posterior sampling reinforcement learning with function approximationby Yingru Li, Zhi-Quan LuoFirst submitted…
Independent RL for Cooperative-Competitive Agents: A Mean-Field Perspectiveby Muhammad Aneeq uz Zaman, Alec Koppel, Mathieu…
A Simple Mixture Policy Parameterization for Improving Sample Efficiency of CVaR Optimizationby Yudong Luo, Yangchen…
Phasic Diversity Optimization for Population-Based Reinforcement Learningby Jingcheng Jiang, Haiyin Piao, Yu Fu, Yihang Hao,…