[edit]
Probabilistic Constrained Reinforcement Learning with Formal Interpretability
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:51303-51327, 2024.
Abstract
Reinforcement learning can provide effective reasoning for sequential decision-making problems with variable dynamics. Such reasoning in practical implementation, however, poses a persistent challenge in interpreting the reward function and the corresponding optimal policy. Consequently, representing sequential decision-making problems as probabilistic inference can have considerable value, as, in principle, the inference offers diverse and powerful mathematical tools to infer the stochastic dynamics whilst suggesting a probabilistic interpretation of policy optimization. In this study, we propose a novel Adaptive Wasserstein Variational Optimization, namely AWaVO, to tackle these interpretability challenges. Our approach uses formal methods to achieve the interpretability: convergence guarantee, training transparency, and intrinsic decision-interpretation. To demonstrate its practicality, we showcase guaranteed interpretability including a global convergence rate $\Theta(1/\sqrt{T})$ not only in simulation but also in real-world quadrotor tasks. In comparison with state-of-the-art benchmarks, including TRPO-IPO, PCPO, and CRPO, we empirically verify that AWaVO offers a reasonable trade-off between high performance and sufficient interpretability.