CAPO: A Unified Policy Gradient Approach for Reward and Cost Optimization in Safe Reinforcement Learning (Student Abstract)

In safe reinforcement learning (SRL), there exists an inherent conflict between maximizing reward and minimizing cost. We propose a novel approach that effectively resolve the conflict between maximizing reward and minimizing cost in joint optimization.When the cost exceeds the threshold, we perform cost-reducing updates. Otherwise, we compute policy gradients that maximize expected rewards, while using second-order Taylor approximation to evaluate whether these reward-maximizing gradients would violate the cost constraint. If constraint violation is detected, we adjust the gradient direction to maintain safety compliance; otherwise, we execute standard reward-increasing policy updates. This approach helps ensure that reward-seeking updates do not inadvertently increase costs, thereby reducing the likelihood of constraint violations. Empirical tests show our framework successfully manages reward-cost trade-offs through reward augmentation and cost shaping, improving both performance and safety without switching optimization strategies. Results demonstrate that concurrent treatment of both objectives in one policy gradient update is viable for improving safe reinforcement learning methods.