Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.17468 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911525255512064 |
|---|---|
| author | Ma, Hao Pu, Zhiqiang Ai, Xiaolin Wang, Huimu |
| author_facet | Ma, Hao Pu, Zhiqiang Ai, Xiaolin Wang, Huimu |
| contents | We present GuidedSAC, a novel reinforcement learning (RL) algorithm that facilitates efficient exploration in vast state-action spaces. GuidedSAC leverages large language models (LLMs) as intelligent supervisors that provide action-level guidance for the Soft Actor-Critic (SAC) algorithm. The LLM-based supervisor analyzes the most recent trajectory using state information and visual replays, offering action-level interventions that enable targeted exploration. Furthermore, we provide a theoretical analysis of GuidedSAC, proving that it preserves the convergence guarantees of SAC while improving convergence speed. Through experiments in both discrete and continuous control environments, including toy text tasks and complex MuJoCo benchmarks, we demonstrate that GuidedSAC consistently outperforms standard SAC and state-of-the-art exploration-enhanced variants (e.g., RND, ICM, and E3B) in terms of sample efficiency and final performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_17468 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Efficient Soft Actor-Critic with LLM-Based Action-Level Guidance for Continuous Control Ma, Hao Pu, Zhiqiang Ai, Xiaolin Wang, Huimu Machine Learning We present GuidedSAC, a novel reinforcement learning (RL) algorithm that facilitates efficient exploration in vast state-action spaces. GuidedSAC leverages large language models (LLMs) as intelligent supervisors that provide action-level guidance for the Soft Actor-Critic (SAC) algorithm. The LLM-based supervisor analyzes the most recent trajectory using state information and visual replays, offering action-level interventions that enable targeted exploration. Furthermore, we provide a theoretical analysis of GuidedSAC, proving that it preserves the convergence guarantees of SAC while improving convergence speed. Through experiments in both discrete and continuous control environments, including toy text tasks and complex MuJoCo benchmarks, we demonstrate that GuidedSAC consistently outperforms standard SAC and state-of-the-art exploration-enhanced variants (e.g., RND, ICM, and E3B) in terms of sample efficiency and final performance. |
| title | Efficient Soft Actor-Critic with LLM-Based Action-Level Guidance for Continuous Control |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2603.17468 |