Stephane Hatgis-Kessell
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1AI×1
Frequent co-authors
Research Timeline
2026
When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?
The paper introduces Prompted Policy Optimization (PromptPO), an LLM-based method that successfully optimizes policies for various sequential RL tasks, demonstrating that LLMs can replace classical RL algorithms when prior knowledge is available, though they struggle with fine-grained continuous control.
Highlighted terms show continued research focus across papers