← Search

Kamalesh Kalirathinam

2 accepted papers

2025

Prompted Policy Search: Reinforcement Learning through Linguistic and Numerical Reasoning in LLMs

NeurIPS 2025poster

Reinforcement Learning (RL) traditionally relies on scalar reward signals, limiting its ability to leverage the rich semantic knowledge often available in real-world tasks. In contrast, humans learn efficiently by combining numerical feedback with language, prior knowledge, and common sense. We intr…

Cited by 0SourceScholar
2025

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement

ICRA 2025

We demonstrate the ability of large language models (LLMs) to perform iterative self-improvement of robot policies. An important insight of this paper is that LLMs have a built-in ability to perform (stochastic) numerical optimization and that this property can be leveraged for explainable robot pol

Cited by 3SourceScholar