Constraint-Adaptive Policy Switching for Offline Safe Reinforcement Learning
Yassine Chemingui, Aryan Deshwal, Honghao Wei, Alan Fern, Jana Doppa
Abstract
Offline safe reinforcement learning (OSRL) involves learning a decision-making policy to maximize rewards from a fixed batch of training data to satisfy pre-defined safety constraints. However, adapting to varying safety constraints during deployment without retraining remains an under-explored challenge. To address this challenge, we introduce constraint-adaptive policy switching (CAPS), a wrapper framework around existing offline RL algorithms. During training, CAPS uses offline data to learn multiple policies with a shared representation that optimize different reward and cost trade-offs. During testing, CAPS switches between those policies by selecting at each state the policy that maximizes future rewards among those that satisfy the current cost constraint. Our experiments on 38 tasks from the DSRL benchmark demonstrate that CAPS consistently outperforms existing methods, establishing a strong wrapper-based baseline for OSRL.
BibTeX
@article{Chemingui_Deshwal_Wei_Fern_Doppa_2025, title={Constraint-Adaptive Policy Switching for Offline Safe Reinforcement Learning}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/33726}, DOI={10.1609/aaai.v39i15.33726}, abstractNote={Offline safe reinforcement learning (OSRL) involves learning a decision-making policy to maximize rewards from a fixed batch of training data to satisfy pre-defined safety constraints. However, adapting to varying safety constraints during deployment without retraining remains an under-explored challenge. To address this challenge, we introduce constraint-adaptive policy switching (CAPS), a wrapper framework around existing offline RL algorithms. During training, CAPS uses offline data to learn multiple policies with a shared representation that optimize different reward and cost trade-offs. During testing, CAPS switches between those policies by selecting at each state the policy that maximizes future rewards among those that satisfy the current cost constraint. Our experiments on 38 tasks from the DSRL benchmark demonstrate that CAPS consistently outperforms existing methods, establishing a strong wrapper-based baseline for OSRL.}, number={15}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Chemingui, Yassine and Deshwal, Aryan and Wei, Honghao and Fern, Alan and Doppa, Jana}, year={2025}, month={Apr.}, pages={15722-15730} }