Predictable Reinforcement Learning Dynamics Through Entropy Rate Minimization

Abstract

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 hum

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyornia2023predictable

Related papers

• Arbitrary Entropy Policy Optimization Breaks The Exploration Bottleneck Of Reinforcement Learning (2025)0.00
• A Comparative Theoretical Analysis Of Entropy Control Methods In Reinforcement Learning (2026)0.00
• Optimal Scheduling Of Entropy Regulariser For Continuous-time Linear-quadratic Reinforcement Learning (2022)4.52
• Rethinking Entropy Interventions In RLVR: An Entropy Change Perspective (2026)0.00
• Surprise-adaptive Intrinsic Motivation For Unsupervised Reinforcement Learning (2024)0.00
• Agentic Entropy-balanced Policy Optimization (2025)0.00
• Do You Need The Entropy Reward (in Practice)? (2022)0.00
• Maximum Entropy RL (provably) Solves Some Robust RL Problems (2021)0.00