Pengfei Wang
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
AI×1ML×1
Frequent co-authors
Research Timeline
2026
Regularized Offline Policy Optimization with Posterior Hybrid Bayesian Belief
The paper introduces Posterior Hybrid Bayesian Belief (PhyB), a novel framework that reformulates policy optimization in Bayesian Offline RL by approximating expectations as a convex combination over a subset of dynamics models, achieving state-of-the-art performance.
Highlighted terms show continued research focus across papers