2023/11/30 by Daniel Jarne Ornia, Ornia, Daniel Jarne, Giannis Delimpaltadakis +5
Computer Science · #Artificial Intelligence (cs.AI) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Reinforcement Learning in Robotics #Systems and Control (eess.SY) #electronic engineering #information engineering
paper · doi:10.48550/arxiv.2311.18703
openalex publication_date 2023/11/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In Reinforcement Learning (RL), agents have no incentive to exhibit predictable behaviors, and are often pushed (through e.g. policy entropy regularisation) to randomise their actions in favor of exploration. This often makes it challenging for other agents and humans to predict an agent's behavior, triggering unsafe scenarios (e.g. in human-robot interaction). We propose a novel method to induce predictable behavior in RL agents, termed Predictability-Aware RL (PARL), employing the agent's trajectory entropy rate to quantify predictability. Our method maximizes a linear combination of a standard discounted reward and the negative entropy rate, thus trading off optimality with predictability. We show how the entropy rate can be formally cast as an average reward, how entropy-rate value functions can be estimated from a learned model and incorporate this in policy-gradient algorithms, and demonstrate how this approach produces predictable (near-optimal) policies in tasks inspired by human-robot use-cases.