Bayesian Bellman Operators

by   Matthew Fellows, et al.

We introduce a novel perspective on Bayesian reinforcement learning (RL); whereas existing approaches infer a posterior over the transition distribution or Q-function, we characterise the uncertainty in the Bellman operator. Our Bayesian Bellman operator (BBO) framework is motivated by the insight that when bootstrapping is introduced, model-free approaches actually infer a posterior over Bellman operators, not value functions. In this paper, we use BBO to provide a rigorous theoretical analysis of model-free Bayesian RL to better understand its relationshipto established frequentist RL methodologies. We prove that Bayesian solutions are consistent with frequentist RL solutions, even when approximate inference isused, and derive conditions for which convergence properties hold. Empirically, we demonstrate that algorithms derived from the BBO framework have sophisticated deep exploration properties that enable them to solve continuous control tasks at which state-of-the-art regularised actor-critic algorithms fail catastrophically


page 1

page 2

page 3

page 4


Exploration with Multi-Sample Target Values for Distributional Reinforcement Learning

Distributional reinforcement learning (RL) aims to learn a value-network...

Bayesian Exploration Networks

Bayesian reinforcement learning (RL) offers a principled and elegant app...

Bayesian Reinforcement Learning: A Survey

Bayesian methods for machine learning have been widely investigated, yie...

Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning

We present DrQ-v2, a model-free reinforcement learning (RL) algorithm fo...

Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic

Learning high-quality Q-value functions plays a key role in the success ...

Latent State Marginalization as a Low-cost Approach for Improving Exploration

While the maximum entropy (MaxEnt) reinforcement learning (RL) framework...

Revisiting the Softmax Bellman Operator: Theoretical Properties and Practical Benefits

The softmax function has been primarily employed in reinforcement learni...

Please sign up or login with your details

Forgot password? Click here to reset