Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.15345 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912389162598400 |
|---|---|
| author | Kooi, Jacob E. Yang, Zhao François-Lavet, Vincent |
| author_facet | Kooi, Jacob E. Yang, Zhao François-Lavet, Vincent |
| contents | Neural network architectures have a large impact in machine learning. In reinforcement learning, network architectures have remained notably simple, as changes often lead to small gains in performance. This work introduces a novel encoder architecture for pixel-based model-free reinforcement learning. The Hadamax (\textbf{Hada}mard \textbf{max}-pooling) encoder achieves state-of-the-art performance by max-pooling Hadamard products between GELU-activated parallel hidden layers. Based on the recent PQN algorithm, the Hadamax encoder achieves state-of-the-art model-free performance in the Atari-57 benchmark. Specifically, without applying any algorithmic hyperparameter modifications, Hadamax-PQN achieves an 80\% performance gain over vanilla PQN and significantly surpasses Rainbow-DQN. For reproducibility, the full code is available on \href{https://github.com/Jacobkooi/Hadamax}{GitHub}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_15345 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hadamax Encoding: Elevating Performance in Model-Free Atari Kooi, Jacob E. Yang, Zhao François-Lavet, Vincent Machine Learning Artificial Intelligence Neural network architectures have a large impact in machine learning. In reinforcement learning, network architectures have remained notably simple, as changes often lead to small gains in performance. This work introduces a novel encoder architecture for pixel-based model-free reinforcement learning. The Hadamax (\textbf{Hada}mard \textbf{max}-pooling) encoder achieves state-of-the-art performance by max-pooling Hadamard products between GELU-activated parallel hidden layers. Based on the recent PQN algorithm, the Hadamax encoder achieves state-of-the-art model-free performance in the Atari-57 benchmark. Specifically, without applying any algorithmic hyperparameter modifications, Hadamax-PQN achieves an 80\% performance gain over vanilla PQN and significantly surpasses Rainbow-DQN. For reproducibility, the full code is available on \href{https://github.com/Jacobkooi/Hadamax}{GitHub}. |
| title | Hadamax Encoding: Elevating Performance in Model-Free Atari |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2505.15345 |