Reccover: Detecting Causal Confusion For Explainable Reinforcement Learning

Abstract

Despite notable results in various fields over the recent years, deep reinforcement learning (DRL) algorithms lack transparency, affecting user trust and hindering their deployment to high-risk tasks. Causal confusion refers to a phenomenon where an agent learns spurious correlations between features which might not hold across the entire state space, preventing safe deployment to real tasks where such correlations might be broken. In this work, we examine whether an agent relies on spurious correlations in critical states, and propose an alternative subset of features on which it should base its decisions instead, to make it less susceptible to causal confusion. Our goal is to increase transparency of DRL agents by exposing the influence of learned spurious correlations on its decisions, and offering advice to developers about feature selection in different parts of state space, to avoid causal confusion. We propose ReCCoVER, an algorithm which detects causal confusion in agent's reas

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keygajcin2022reccover

Related papers

• Causal State Distillation For Explainable Reinforcement Learning (2023)0.00
• A Survey On Explainable Reinforcement Learning: Concepts, Algorithms, Challenges (2022)0.00
• Redefining Counterfactual Explanations For Reinforcement Learning: Overview, Challenges And Opportunities (2022)0.00
• Explainable Reinforcement Learning Via A Causal World Model (2023)9.03
• RACCER: Towards Reachable And Certain Counterfactual Explanations For Reinforcement Learning (2023)0.00
• Experiential Explanations For Reinforcement Learning (2022)2.26
• Explainable Reinforcement Learning Through A Causal Lens (2019)16.69
• Learning Nonlinear Causal Reductions To Explain Reinforcement Learning Policies (2025)0.00