"pessimistic policy learning" Papers
2 papers found
Policy learning “without” overlap: Pessimism and generalized empirical Bernstein’s inequality
Ying Jin, Zhimei Ren, Zhuoran Yang et al.
NeurIPS 2025posterarXiv:2212.09900
30
citations
REINFORCEMENT LEARNING FOR INDIVIDUAL OPTIMAL POLICY FROM HETEROGENEOUS DATA
Rui Miao, Babak Shahbaba, Annie Qu
NeurIPS 2025posterarXiv:2505.09496
1
citations