no code implementations • 4 Apr 2024 • Darioush Kevian, Usman Syed, Xingang Guo, Aaron Havens, Geir Dullerud, Peter Seiler, Lianhui Qin, Bin Hu
In this paper, we explore the capabilities of state-of-the-art large language models (LLMs) such as GPT-4, Claude 3 Opus, and Gemini 1. 0 Ultra in solving undergraduate-level control problems.
no code implementations • 18 Feb 2024 • Darioush Keivan, Xingang Guo, Peter Seiler, Geir Dullerud, Bin Hu
Built upon such a policy optimization persepctive, our paper extends these subgradient-based search methods to a model-free setting.
1 code implementation • 13 Feb 2024 • Xingang Guo, Fangxu Yu, huan zhang, Lianhui Qin, Bin Hu
Based on this connection, we adapt the Energy-based Constrained Decoding with Langevin Dynamics (COLD), a state-of-the-art, highly efficient algorithm in controllable text generation, and introduce the COLD-Attack framework which unifies and automates the search of adversarial LLM attacks under a variety of control requirements such as fluency, stealthiness, sentiment, and left-right-coherence.
no code implementations • 20 Oct 2022 • Xingang Guo, Bin Hu
In this work, we show that direct policy search is guaranteed to find the global solution of the robust $\mathcal{H}_\infty$ state-feedback control design problem.
no code implementations • 20 Apr 2022 • Xingang Guo, Bin Hu
In this paper, we consider the policy evaluation problem in multi-agent reinforcement learning (MARL) and derive exact closed-form formulas for the finite-time mean-squared estimation errors of decentralized temporal difference (TD) learning with linear function approximation.
no code implementations • 14 Feb 2022 • Xingang Guo, Bin Hu
Value-based methods play a fundamental role in Markov decision processes (MDPs) and reinforcement learning (RL).