Enhancing Human-Likeness in Reinforcement Learning Agents via Hierarchical Macro Action Quantization
This work addresses the problem of creating more human-like and interpretable RL agents, which is important for applications where human-agent interaction and trust are critical.
This paper introduces a novel human-like reinforcement learning framework, HiMAQ, which uses hierarchical macro action quantization to predict action sequences aligned with human behaviors while maximizing rewards. Evaluated on D4RL benchmarks, HiMAQ outperforms its non-hierarchical baseline (MAQ) in human-likeness scores and maintains comparable or better success rates than previous RL agents.
Human-like agents are a long-standing goal of artificial intelligence. Despite strong performance, most reinforcement learning (RL) agents remain reward-driven and often exhibit behaviors that differ from humans, limiting interpretability and reliability. In this work, we introduce a novel human-like RL framework that predicts action sequences closely aligned with human behaviors while maximizing rewards. Specifically, we encode human demonstrations into macro actions using a hierarchical macro action quantization approach (termed HiMAQ) consisting of two successive levels of vector quantization. The lower quantization level maps input actions to fine-grained subaction clusters, while the higher quantization level aggregates these subaction clusters into action clusters. Extensive evaluations on the D4RL benchmarks show that our hierarchical approach outperforms the non-hierarchical baseline (MAQ), achieving better human-likeness scores while maintaining comparable or better success rates than previous RL agents. The improvements generalize across integrations with various RL algorithms, namely IQL, SAC, and RLPD.