OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning

TL;DR

OASIS introduces a novel offline safe RL method using a conditional diffusion model to synthesize datasets, improving safety, data efficiency, and performance in constrained environments.

Contribution

The paper proposes OASIS, a new paradigm employing conditional diffusion models to shape offline datasets for enhanced safe reinforcement learning.

Findings

Outperforms existing methods on public benchmarks.

Achieves high reward and safety compliance.

Demonstrates robustness and data efficiency.

Abstract

Offline safe reinforcement learning (RL) aims to train a policy that satisfies constraints using a pre-collected dataset. Most current methods struggle with the mismatch between imperfect demonstrations and the desired safe and rewarding performance. In this paper, we introduce OASIS (cOnditionAl diStributIon Shaping), a new paradigm in offline safe RL designed to overcome these critical limitations. OASIS utilizes a conditional diffusion model to synthesize offline datasets, thus shaping the data distribution toward a beneficial target domain. Our approach makes compliance with safety constraints through effective data utilization and regularization techniques to benefit offline safe RL training. Comprehensive evaluations on public benchmarks and varying datasets showcase OASIS's superiority in benefiting offline safe RL agents to achieve high-reward behavior while satisfying the safety constraints, outperforming established baselines. Furthermore, OASIS exhibits high data efficiency and robustness, making it suitable for real-world applications, particularly in tasks where safety is imperative and high-quality demonstrations are scarce.