Year: 2025
Type: preprint
Abstract: This paper proposes a simulation-based reinforcement learning algorithm for controlling systems with uncertain and varying system parameters. While simulators are useful for safely learning control policies, the reality gap remains a major challenge. To alleviate this challenge, we propose a two-stage algorithm. First, multiple control policies are learned for systems with different system parameters in a simulator. Second, for a real system, the control policies are adaptively switched using an online convex optimization algorithm based on observations. This approach is expected to reduce learning complexity compared with existing approaches that rely on a single policy to address the reality gap.
Source: arXiv (Cornell University)
Author: Ikemoto, Junya
Institution: The University of Osaka
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4416618345