Value-distributional Model-based Reinforcement Learning

Abstract

Quantifying uncertainty about a policy's long-term performance is important to solve sequential decision-making tasks. We study the problem from a model-based Bayesian reinforcement learning perspective, where the goal is to learn the posterior distribution over value functions induced by parameter (epistemic) uncertainty of the Markov decision process. Previous work restricts the analysis to a few moments of the distribution over values or imposes a particular distribution shape, e.g., Gaussians. Inspired by distributional reinforcement learning, we introduce a Bellman operator whose fixed-point is the value distribution function. Based on our theory, we propose Epistemic Quantile-Regression (EQR), a model-based algorithm that learns a value distribution function. We combine EQR with soft actor-critic (SAC) for policy optimization with an arbitrary differentiable objective function of the learned value distribution. Evaluation across several continuous-control tasks shows performance

Stats

• citations0
• S2 citations—
• github stars5
• HF likes0
• heat score1.56
• arxiv keyluis2023value

Related papers

• Model-based Epistemic Variance Of Values For Risk-aware Policy Optimization (2023)0.00
• Distributional Reinforcement Learning With Quantile Regression (2017)19.20
• A Distributional Perspective On Reinforcement Learning (2017)0.00
• Distributional Soft Actor-critic: Off-policy Reinforcement Learning For Addressing Value Estimation Errors (2020)17.77
• Distributional Soft Actor-critic With Diffusion Policy (2025)0.00
• Normality-guided Distributional Reinforcement Learning For Continuous Control (2022)0.00
• The Statistical Benefits Of Quantile Temporal-difference Learning For Value Estimation (2023)0.00
• Uncertainty Quantification And Exploration For Reinforcement Learning (2019)6.77