Bayesian Residual Policy Optimization: Scalable Bayesian Reinforcement Learning With Clairvoyant Experts

Abstract

Informed and robust decision making in the face of uncertainty is critical for robots that perform physical tasks alongside people. We formulate this as Bayesian Reinforcement Learning over latent Markov Decision Processes (MDPs). While Bayes-optimality is theoretically the gold standard, existing algorithms do not scale well to continuous state and action spaces. Our proposal builds on the following insight: in the absence of uncertainty, each latent MDP is easier to solve. We first obtain an ensemble of experts, one for each latent MDP, and fuse their advice to compute a baseline policy. Next, we train a Bayesian residual policy to improve upon the ensemble's recommendation and learn to reduce uncertainty. Our algorithm, Bayesian Residual Policy Optimization (BRPO), imports the scalability of policy gradient methods and task-specific expert skills. BRPO significantly improves the ensemble of experts and drastically outperforms existing adaptive RL methods.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylee2020bayesian

Related papers

• Bayesian Policy Optimization For Model Uncertainty (2018)0.00
• Think Outside The Policy: In-context Steered Policy Optimization (2025)0.00
• Uncertainty-aware Policy Optimization: A Robust, Adaptive Trust Region Approach (2020)0.00
• Robust Model-free Reinforcement Learning With Multi-objective Bayesian Optimization (2019)11.08
• Asymptotically Optimal Reinforcement Learning In Block Markov Decision Processes (2025)0.00
• Probabilistic Mixture-of-experts For Efficient Deep Reinforcement Learning (2021)0.00
• Continuous Action Reinforcement Learning From A Mixture Of Interpretable Experts (2020)0.00
• Efficient Deep Reinforcement Learning With Predictive Processing Proximal Policy Optimization (2022)0.00