Risk Sensitive Model-Based Reinforcement Learning using Uncertainty Guided Planning

Abstract

Identifying uncertainty and taking mitigating actions is crucial for safe and trustworthy reinforcement learning agents, especially when deployed in high-risk environments. In this paper, risk sensitivity is promoted in a model-based reinforcement learning algorithm by exploiting the ability of a bootstrap ensemble of dynamics models to estimate environment epistemic uncertainty. We propose uncertainty guided cross-entropy method planning, which penalises action sequences that result in high variance state predictions during model rollouts, guiding the agent to known areas of the state space with low uncertainty. Experiments display the ability for the agent to identify uncertain regions of the state space during planning and to take actions that maintain the agent within high confidence areas, without the requirement of explicit constraints. The result is a reduction in the performance in terms of attaining reward, displaying a trade-off between risk and return.

Safe RL Workshop NeurIPS 2021

References in corpus (9)

• Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
• Safe Exploration in Continuous Action Spaces
• Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
• Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning
• A Lyapunov-based Approach to Safe Reinforcement Learning
• Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings
• SAMBA: Safe Model-Based & Active Reinforcement Learning
• MBRL-Lib: A Modular Library for Model-based Reinforcement Learning
• Constrained Model-based Reinforcement Learning with Robust Cross-Entropy Method