Boosting Hierarchical Reinforcement Learning with Meta-Learning for Complex Task Adaptation
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929760858275840 |
|---|---|
| author | Khajooeinejad, Arash Masoumi, Fatemeh Sadat Chapariniya, Masoumeh |
| author_facet | Khajooeinejad, Arash Masoumi, Fatemeh Sadat Chapariniya, Masoumeh |
| contents | Hierarchical Reinforcement Learning (HRL) is well-suitedd for solving complex tasks by breaking them down into structured policies. However, HRL agents often struggle with efficient exploration and quick adaptation. To overcome these limitations, we propose integrating meta-learning into HRL to enable agents to learn and adapt hierarchical policies more effectively. Our method leverages meta-learning to facilitate rapid task adaptation using prior experience, while intrinsic motivation mechanisms drive efficient exploration by rewarding the discovery of novel states. Specifically, our agent employs a high-level policy to choose among multiple low-level policies within custom-designed grid environments. By incorporating gradient-based meta-learning with differentiable inner-loop updates, we optimize performance across a curriculum of progressively challenging tasks. Experimental results highlight that our metalearning-enhanced hierarchical agent significantly outperforms standard HRL approaches lacking meta-learning and intrinsic motivation. The agent demonstrates faster learning, greater cumulative rewards, and higher success rates in complex grid-based scenarios. These Findings underscore the effectiveness of combining meta-learning, curriculum learning, and intrinsic motivation to enhance the capability of HRL agents in tackling complex tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_07921 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Boosting Hierarchical Reinforcement Learning with Meta-Learning for Complex Task Adaptation Khajooeinejad, Arash Masoumi, Fatemeh Sadat Chapariniya, Masoumeh Machine Learning Artificial Intelligence Hierarchical Reinforcement Learning (HRL) is well-suitedd for solving complex tasks by breaking them down into structured policies. However, HRL agents often struggle with efficient exploration and quick adaptation. To overcome these limitations, we propose integrating meta-learning into HRL to enable agents to learn and adapt hierarchical policies more effectively. Our method leverages meta-learning to facilitate rapid task adaptation using prior experience, while intrinsic motivation mechanisms drive efficient exploration by rewarding the discovery of novel states. Specifically, our agent employs a high-level policy to choose among multiple low-level policies within custom-designed grid environments. By incorporating gradient-based meta-learning with differentiable inner-loop updates, we optimize performance across a curriculum of progressively challenging tasks. Experimental results highlight that our metalearning-enhanced hierarchical agent significantly outperforms standard HRL approaches lacking meta-learning and intrinsic motivation. The agent demonstrates faster learning, greater cumulative rewards, and higher success rates in complex grid-based scenarios. These Findings underscore the effectiveness of combining meta-learning, curriculum learning, and intrinsic motivation to enhance the capability of HRL agents in tackling complex tasks. |
| title | Boosting Hierarchical Reinforcement Learning with Meta-Learning for Complex Task Adaptation |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2410.07921 |