Bayesian Bellman Operators

06/09/2021
by   Matthew Fellows, et al.
0

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

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

12/11/2020

OPAC: Opportunistic Actor-Critic

Actor-critic methods, a type of model-free reinforcement learning (RL), ...
09/14/2016

Bayesian Reinforcement Learning: A Survey

Bayesian methods for machine learning have been widely investigated, yie...
07/20/2021

Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning

We present DrQ-v2, a model-free reinforcement learning (RL) algorithm fo...
07/02/2020

ε-BMC: A Bayesian Ensemble Approach to Epsilon-Greedy Exploration in Model-Free Reinforcement Learning

Resolving the exploration-exploitation trade-off remains a fundamental p...
11/03/2018

VIREL: A Variational Inference Framework for Reinforcement Learning

Applying probabilistic models to reinforcement learning (RL) has become ...
12/02/2018

Revisiting the Softmax Bellman Operator: Theoretical Properties and Practical Benefits

The softmax function has been primarily employed in reinforcement learni...
11/30/2021

Continuous Control With Ensemble Deep Deterministic Policy Gradients

The growth of deep reinforcement learning (RL) has brought multiple exci...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.