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

Marin Vlastelica, Sebastian Blaes, Cristina Pineri, Georg Martius
9/11/2023
cs.LGcs.AIcs.RO

No confident code implementation found for this paper.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Risk-Sensitive and Robust Model-Based Reinforcement Learning and Planning

86% match2023

Practical Probabilistic Model-based Deep Reinforcement Learning by Integrating Dropout Uncertainty and Trajectory Sampling

84% match1 repo162023

Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning

84% match2026

Decision-Making Under Uncertainty: Beyond Probabilities

83% match2023

Probabilistic Artificial Intelligence

83% match2025

Deep Gaussian Covariance Network with Trajectory Sampling for Data-Efficient Policy Search

82% match2024

Cite this paper

@article{vlastelica2023mind,
  title  = {Mind the Uncertainty: Risk-Aware and Actively Exploring Model-Based Reinforcement Learning},
  author = {Marin Vlastelica and Sebastian Blaes and Cristina Pineri and Georg Martius},
  year   = {2023},
  eprint = {2309.05582},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2309.05582v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2309.05582.svg)](https://codeofpaper.com/paper/2309.05582)

Discussion