Latent Safety-Constrained Policy Approach for Safe Offline Reinforcement Learning
This addresses the challenge of balancing safety and performance in offline RL, which is crucial for real-world applications like autonomous driving, though it appears incremental in method.
The paper tackles the problem of safe offline reinforcement learning by developing a policy that maximizes cumulative rewards while strictly adhering to safety constraints using only offline data. The approach achieves safety compliance and excels in cumulative reward optimization, surpassing existing methods in benchmark datasets including autonomous driving scenarios.
In safe offline reinforcement learning (RL), the objective is to develop a policy that maximizes cumulative rewards while strictly adhering to safety constraints, utilizing only offline data. Traditional methods often face difficulties in balancing these constraints, leading to either diminished performance or increased safety risks. We address these issues with a novel approach that begins by learning a conservatively safe policy through the use of Conditional Variational Autoencoders, which model the latent safety constraints. Subsequently, we frame this as a Constrained Reward-Return Maximization problem, wherein the policy aims to optimize rewards while complying with the inferred latent safety constraints. This is achieved by training an encoder with a reward-Advantage Weighted Regression objective within the latent constraint space. Our methodology is supported by theoretical analysis, including bounds on policy performance and sample complexity. Extensive empirical evaluation on benchmark datasets, including challenging autonomous driving scenarios, demonstrates that our approach not only maintains safety compliance but also excels in cumulative reward optimization, surpassing existing methods. Additional visualizations provide further insights into the effectiveness and underlying mechanisms of our approach.