Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning

TL;DR

This paper introduces a primal-based framework for safe multi-objective reinforcement learning that balances multiple goals with safety constraints, using a novel natural policy gradient method and providing theoretical guarantees.

Contribution

It proposes a new natural policy gradient manipulation technique for constrained multi-objective RL and establishes convergence and safety guarantees.

Findings

Outperforms prior methods on challenging safe RL tasks

Provides theoretical convergence and constraint violation guarantees

Effectively balances multiple objectives with safety constraints

Abstract

In numerous reinforcement learning (RL) problems involving safety-critical systems, a key challenge lies in balancing multiple objectives while simultaneously meeting all stringent safety constraints. To tackle this issue, we propose a primal-based framework that orchestrates policy optimization between multi-objective learning and constraint adherence. Our method employs a novel natural policy gradient manipulation method to optimize multiple RL objectives and overcome conflicting gradients between different tasks, since the simple weighted average gradient direction may not be beneficial for specific tasks' performance due to misaligned gradients of different task objectives. When there is a violation of a hard constraint, our algorithm steps in to rectify the policy to minimize this violation. We establish theoretical convergence and constraint violation guarantees in a tabular setting. Empirically, our proposed method also outperforms prior state-of-the-art methods on challenging safe multi-objective reinforcement learning tasks.