1
Regularized Offline Policy Optimization with Posterior Hybrid Bayesian Belief
离线强化学习新范式：后验混合贝叶斯信念正则化策略优化，破解分布外动作评估难题
arXiv:2606.00680v1 Announce Type: cross Abstract: Offline reinforcement learning (RL) aims to optimize policies from pre-collected datasets. A bottlen…