Geir E. Dullerud

Adaptive deep reinforcement learning for non-stationary environments

Science China Information Sciences · 2022 · 33 citations

$\mathcal {L}_2$-Gain Analysis of Periodic Event-Triggered Control and Self-Triggered Control Using Lifting

IEEE Transactions on Automatic Control · 2020 · 22 citations

We analyze the stability, and <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">L</i> <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> -gain properties of a class of hybrid systems that exhibit time-varying linear flow dynamics, periodic time-triggered jumps, and arbitrary nonlinear jump maps. This class of hybrid systems encompasses periodic event-triggered control, self-triggered control, and netwo…

Capabilities of Large Language Models in Control Engineering: A Benchmark Study on GPT-4, Claude 3 Opus, and Gemini 1.0 Ultra

arXiv (Cornell University) · 2024-04-04 · 19 citations

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. Controls provides an interesting case study for LLM reasoning due to its combination of mathematical theory and engineering design. We introduce ControlBench, a benchmark dataset tailored to reflect the breadth, depth, and complexity of classical control design. We use this dataset to study and evaluate the…

Model-Based Offline Reinforcement Learning With Uncertainty Estimation and Policy Constraint

IEEE Transactions on Artificial Intelligence · 2024-03-05 · 8 citations

Explicit uncertainty estimation is an effective method for addressing the overestimation problem caused by distribution shifts in offline RL. However, the common bootstrapped ensemble network method fails to obtain reliable uncertainty estimation, which will decrease the performance of offline RL. Compared with model-free offline RL, model-based offline RL provides better generalizability although it is limited by the model-bias problem. The adverse effects of model bias will be aggravated by th…

Convergence of Gradient-based MAML in LQR

2023-12-13 · 6 citations

The main objective of this research paper is to investigate the local convergence characteristics of Model-agnostic Meta-learning (MAML) when applied to linear system quadratic optimal control (LQR). MAML and its variations have become popular techniques for quickly adapting to new tasks by leveraging previous learning knowledge in areas like regression, classification, and reinforcement learning. However, its theoretical guarantees remain unknown due to non-convexity and its structure, making i…