Alternating Optimisation and Quadrature for Robust Control
This addresses the challenge of robust policy learning in reinforcement learning for simulation-based domains, though it appears incremental as it builds on existing Bayesian methods.
The paper tackles the problem of learning robust policies in simulators by adjusting controllable environment variables, presenting ALOQ, which uses Bayesian optimisation and quadrature to handle rare events, resulting in more efficient and robust learning compared to existing methods.
Bayesian optimisation has been successfully applied to a variety of reinforcement learning problems. However, the traditional approach for learning optimal policies in simulators does not utilise the opportunity to improve learning by adjusting certain environment variables: state features that are unobservable and randomly determined by the environment in a physical setting but are controllable in a simulator. This paper considers the problem of finding a robust policy while taking into account the impact of environment variables. We present Alternating Optimisation and Quadrature (ALOQ), which uses Bayesian optimisation and Bayesian quadrature to address such settings. ALOQ is robust to the presence of significant rare events, which may not be observable under random sampling, but play a substantial role in determining the optimal policy. Experimental results across different domains show that ALOQ can learn more efficiently and robustly than existing methods.