Multi-Objective Instruction-Aware Representation Learning in Procedural Content Generation RL
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909018754121728 |
|---|---|
| author | Kim, Sung-Hyun Hwang, Geum-Hwan Baek, In-Chang Lee, Seo-Young Kim, Kyung-Joong |
| author_facet | Kim, Sung-Hyun Hwang, Geum-Hwan Baek, In-Chang Lee, Seo-Young Kim, Kyung-Joong |
| contents | Recent advancements in generative modeling emphasize the importance of natural language as a highly expressive and accessible modality for controlling content generation. However, existing instructed reinforcement learning for procedural content generation (IPCGRL) method often struggle to leverage the expressive richness of textual input, especially under complex, multi-objective instructions, leading to limited controllability. To address this problem, we propose \textit{MIPCGRL}, a multi-objective representation learning method for instructed content generators, which incorporates sentence embeddings as conditions. MIPCGRL effectively trains a multi-objective embedding space by incorporating multi-label classification and multi-head regression networks. Experimental results show that the proposed method achieves up to a 13.8\% improvement in controllability with multi-objective instructions. The ability to process complex instructions enables more expressive and flexible content generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_09193 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-Objective Instruction-Aware Representation Learning in Procedural Content Generation RL Kim, Sung-Hyun Hwang, Geum-Hwan Baek, In-Chang Lee, Seo-Young Kim, Kyung-Joong Machine Learning Artificial Intelligence Recent advancements in generative modeling emphasize the importance of natural language as a highly expressive and accessible modality for controlling content generation. However, existing instructed reinforcement learning for procedural content generation (IPCGRL) method often struggle to leverage the expressive richness of textual input, especially under complex, multi-objective instructions, leading to limited controllability. To address this problem, we propose \textit{MIPCGRL}, a multi-objective representation learning method for instructed content generators, which incorporates sentence embeddings as conditions. MIPCGRL effectively trains a multi-objective embedding space by incorporating multi-label classification and multi-head regression networks. Experimental results show that the proposed method achieves up to a 13.8\% improvement in controllability with multi-objective instructions. The ability to process complex instructions enables more expressive and flexible content generation. |
| title | Multi-Objective Instruction-Aware Representation Learning in Procedural Content Generation RL |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2508.09193 |