Hongqiang Lin
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
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.
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.
Papers
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…