Episodic Novelty Through Temporal Distance
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909466527531008 |
|---|---|
| author | Jiang, Yuhua Liu, Qihan Yang, Yiqin Ma, Xiaoteng Zhong, Dianyu Hu, Hao Yang, Jun Liang, Bin Xu, Bo Zhang, Chongjie Zhao, Qianchuan |
| author_facet | Jiang, Yuhua Liu, Qihan Yang, Yiqin Ma, Xiaoteng Zhong, Dianyu Hu, Hao Yang, Jun Liang, Bin Xu, Bo Zhang, Chongjie Zhao, Qianchuan |
| contents | Exploration in sparse reward environments remains a significant challenge in reinforcement learning, particularly in Contextual Markov Decision Processes (CMDPs), where environments differ across episodes. Existing episodic intrinsic motivation methods for CMDPs primarily rely on count-based approaches, which are ineffective in large state spaces, or on similarity-based methods that lack appropriate metrics for state comparison. To address these shortcomings, we propose Episodic Novelty Through Temporal Distance (ETD), a novel approach that introduces temporal distance as a robust metric for state similarity and intrinsic reward computation. By employing contrastive learning, ETD accurately estimates temporal distances and derives intrinsic rewards based on the novelty of states within the current episode. Extensive experiments on various benchmark tasks demonstrate that ETD significantly outperforms state-of-the-art methods, highlighting its effectiveness in enhancing exploration in sparse reward CMDPs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_15418 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Episodic Novelty Through Temporal Distance Jiang, Yuhua Liu, Qihan Yang, Yiqin Ma, Xiaoteng Zhong, Dianyu Hu, Hao Yang, Jun Liang, Bin Xu, Bo Zhang, Chongjie Zhao, Qianchuan Machine Learning Artificial Intelligence Exploration in sparse reward environments remains a significant challenge in reinforcement learning, particularly in Contextual Markov Decision Processes (CMDPs), where environments differ across episodes. Existing episodic intrinsic motivation methods for CMDPs primarily rely on count-based approaches, which are ineffective in large state spaces, or on similarity-based methods that lack appropriate metrics for state comparison. To address these shortcomings, we propose Episodic Novelty Through Temporal Distance (ETD), a novel approach that introduces temporal distance as a robust metric for state similarity and intrinsic reward computation. By employing contrastive learning, ETD accurately estimates temporal distances and derives intrinsic rewards based on the novelty of states within the current episode. Extensive experiments on various benchmark tasks demonstrate that ETD significantly outperforms state-of-the-art methods, highlighting its effectiveness in enhancing exploration in sparse reward CMDPs. |
| title | Episodic Novelty Through Temporal Distance |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2501.15418 |