Optimistic Online LQR via Intrinsic Rewards

arXiv:2603.28938 · eess.SY, cs.LG, cs.SY, math.OC · Submitted 2026-08-21 · Read on arXiv

Marcell Bartos, Bruce D. Lee, Lenart Treven, Andreas Krause, Florian Dörfler, Melanie N. Zeilinger

eess.SY, cs.LG, cs.SY, math.OC

Submitted: 2026-08-21

Updated: 2026-08-24

Code: https://github.com/lenarttreven/lqr_research

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Regret — 37× in this paper · explained in 3 episodes
• Reinforcement Learning — 16× in this paper · explained in 4 episodes
• Regularization — 5× in this paper · explained in 3 episodes
• Action Space — 4× in this paper · explained in 1 episode
• Deep Reinforcement Learning — 4× in this paper · explained in 2 episodes
• Benchmark — 3× in this paper · explained in 2 episodes
• Information Gain — 3× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Q-learning — 1× in this paper · explained in 3 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Sample Efficiency — 1× in this paper · explained in 4 episodes
• System Identification — 1× in this paper · explained in 3 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Playing Atari with Deep Reinforcement Learning
• Training Agents Inside of Scalable World Models
• $\pi^{*}_{0.6}$: a VLA That Learns From Experience
• Policy Gradient Adaptive Control for the LQR: Indirect and Direct Approaches
• Stability of Certainty-Equivalent Adaptive LQR for Linear Systems with Unknown Time-Varying Parameters
• Harnessing Uncertainty for a Separation Principle in Direct Data-Driven Predictive Control
• Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design

Related papers

• One Request, Multiple Experts: LLM Orchestrates Domain Specific Models via Adaptive Task Routing
• A Geometric Decision Procedure for STL Feasibility and Repair
• Submodular Multi-Agent Policy Learning for Online Distributed Task Allocation in Open Multi-Agent Systems
• Policy-Level Recursive Self-Improvement for Embodied AI with a Criticality World Model
• Minimal Experiments for Robust Stabilization: Information, Spectral Geometry, and Duration
• Decentralized Power-Optimal Coordination for Spacecraft Swarms Using Time-Varying Magnetorquer Actuation