1 citations · 1 across the 10 of their papers we have counts for
8 papers · 1 filter
The Fragility of Learning LQG Controllers
Bruce D. Lee, Anastasios Tsiamis, Nikolai Matni +2
Learning methods are increasingly used to synthesize controllers from data, yet existing sample-complexity characterizations for continuous control are sharp only in the fully obse…
Statistical Efficiency of Single- and Multi-step Models for Forecasting and Control
Anne Somalwar, Bruce D. Lee, George J. Pappas +1
Compounding error, where small prediction mistakes accumulate over time, presents a major challenge in learning-based control. A common remedy is to train multi-step predictors dir…
Optimistic Online LQR via Intrinsic Rewards
Marcell Bartos, Bruce D. Lee, Lenart Treven +3
Optimism in the face of uncertainty is a popular approach to balance exploration and exploitation in reinforcement learning. Here, we consider the online linear quadratic regulator…
Learning with Imperfect Models: When Multi-step Prediction Mitigates Compounding Error
Anne Somalwar, Bruce D. Lee, George J. Pappas +1
Compounding error, where small prediction mistakes accumulate over time, presents a major challenge in learning-based control. For example, this issue often limits the performance…
Policy Gradient for LQR with Domain Randomization
Tesshu Fujinami, Bruce D. Lee, Nikolai Matni +1
Domain randomization (DR) enables sim-to-real transfer by training controllers on a distribution of simulated environments, with the goal of achieving robust performance in the rea…
Domain Randomization is Sample Efficient for Linear Quadratic Control
Tesshu Fujinami, Bruce D. Lee, Nikolai Matni +1
We study the sample efficiency of domain randomization and robust control for the benchmark problem of learning the linear quadratic regulator (LQR). Domain randomization, which sy…