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

2023/09/11 by Marin Vlastelica, Sebastian Blaes, Vlastelica, Marin +5 · 1 citation
Computer Science · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Reinforcement Learning in Robotics #Robotics (cs.RO)

paper · pdf · doi:10.48550/arxiv.2309.05582

openalex publication_date 2023/09/11 · openalex created_date 2023/09/13 · openalex updated_date 2026/07/28

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.

Cited by

• Belief-Guided Decision Making with Uncertainty Gating in the Game of Go

Related

• Risk-Sensitive and Robust Model-Based Reinforcement Learning and Planning
• Safe Reinforcement Learning via Probabilistic Shields
• Risk Sensitive Model-Based Reinforcement Learning using Uncertainty\n Guided Planning
• Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
• Acting upon Imagination: when to trust imagined trajectories in model\n based reinforcement learning