CURLing the Dream: Contrastive Representations for World Modeling in Reinforcement Learning
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_ | 1866913487770353664 |
|---|---|
| author | Kich, Victor Augusto Bottega, Jair Augusto Steinmetz, Raul Grando, Ricardo Bedin Yorozu, Ayano Ohya, Akihisa |
| author_facet | Kich, Victor Augusto Bottega, Jair Augusto Steinmetz, Raul Grando, Ricardo Bedin Yorozu, Ayano Ohya, Akihisa |
| contents | In this work, we present Curled-Dreamer, a novel reinforcement learning algorithm that integrates contrastive learning into the DreamerV3 framework to enhance performance in visual reinforcement learning tasks. By incorporating the contrastive loss from the CURL algorithm and a reconstruction loss from autoencoder, Curled-Dreamer achieves significant improvements in various DeepMind Control Suite tasks. Our extensive experiments demonstrate that Curled-Dreamer consistently outperforms state-of-the-art algorithms, achieving higher mean and median scores across a diverse set of tasks. The results indicate that the proposed approach not only accelerates learning but also enhances the robustness of the learned policies. This work highlights the potential of combining different learning paradigms to achieve superior performance in reinforcement learning applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_05781 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CURLing the Dream: Contrastive Representations for World Modeling in Reinforcement Learning Kich, Victor Augusto Bottega, Jair Augusto Steinmetz, Raul Grando, Ricardo Bedin Yorozu, Ayano Ohya, Akihisa Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition In this work, we present Curled-Dreamer, a novel reinforcement learning algorithm that integrates contrastive learning into the DreamerV3 framework to enhance performance in visual reinforcement learning tasks. By incorporating the contrastive loss from the CURL algorithm and a reconstruction loss from autoencoder, Curled-Dreamer achieves significant improvements in various DeepMind Control Suite tasks. Our extensive experiments demonstrate that Curled-Dreamer consistently outperforms state-of-the-art algorithms, achieving higher mean and median scores across a diverse set of tasks. The results indicate that the proposed approach not only accelerates learning but also enhances the robustness of the learned policies. This work highlights the potential of combining different learning paradigms to achieve superior performance in reinforcement learning applications. |
| title | CURLing the Dream: Contrastive Representations for World Modeling in Reinforcement Learning |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.05781 |