2 papers
cs.LG2024
Bayesian Design Principles for Offline-to-Online Reinforcement Learning
Hao Hu, Yiqin Yang, Jianing Ye +7
Offline reinforcement learning (RL) is crucial for real-world applications where exploration can be costly or unsafe. However, offline learned policies are often suboptimal, and fu…
cs.LG2023
Unsupervised Behavior Extraction via Random Intent Priors
Hao Hu, Yiqin Yang, Jianing Ye +2
Reward-free data is abundant and contains rich prior knowledge of human behaviors, but it is not well exploited by offline reinforcement learning (RL) algorithms. In this paper, we…