Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.30928 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914615989895168 |
|---|---|
| author | Nizamani, Usman Luqman, M. Shaheer Fateh, Fawad Javed Ali, Ali Shah Popattia, Murad Zia, M. Zeeshan Tran, Quoc-Huy |
| author_facet | Nizamani, Usman Luqman, M. Shaheer Fateh, Fawad Javed Ali, Ali Shah Popattia, Murad Zia, M. Zeeshan Tran, Quoc-Huy |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_30928 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Enhancing Human-Likeness in Reinforcement Learning Agents via Hierarchical Macro Action Quantization Nizamani, Usman Luqman, M. Shaheer Fateh, Fawad Javed Ali, Ali Shah Popattia, Murad Zia, M. Zeeshan Tran, Quoc-Huy Robotics 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. |
| title | Enhancing Human-Likeness in Reinforcement Learning Agents via Hierarchical Macro Action Quantization |
| topic | Robotics |
| url | https://arxiv.org/abs/2605.30928 |