Mind the Uncertainty: Risk-Aware and Actively Exploring Model-Based Reinforcement Learning

We introduce a simple but effective method for managing risk in model-based reinforcement learning with trajectory sampling that involves probabilistic safety constraints and balancing of optimism in the face of epistemic uncertainty and pessimism in the face of aleatoric uncertainty of an ensemble...

Full description

Saved in:
Bibliographic Details
Main Authors Vlastelica, Marin, Blaes, Sebastian, Pineri, Cristina, Martius, Georg
Format Journal Article
LanguageEnglish
Published 11.09.2023
Subjects
Computer Science - Artificial Intelligence
Computer Science - Learning
Computer Science - Robotics
Online AccessGet full text

Cover

More Information
Summary:We introduce a simple but effective method for managing risk in model-based reinforcement learning with trajectory sampling that involves probabilistic safety constraints and balancing of optimism in the face of epistemic uncertainty and pessimism in the face of aleatoric uncertainty of an ensemble of stochastic neural networks.Various experiments indicate that the separation of uncertainties is essential to performing well with data-driven MPC approaches in uncertain and safety-critical control environments.
DOI:10.48550/arxiv.2309.05582