Model-based Offline Policy Optimization with Adversarial Network

TL;DR

This paper introduces MOAN, a model-based offline RL framework using adversarial learning to improve transition model generalization, uncertainty estimation, and exploration, leading to superior performance on benchmarks.

Contribution

Proposes MOAN, which employs adversarial learning for better generalization and uncertainty quantification in offline RL transition models, addressing over-conservatism and unreliable estimates.

Findings

Outperforms state-of-the-art offline RL baselines

Generates diverse in-distribution samples

Provides more accurate uncertainty quantification

Abstract

Model-based offline reinforcement learning (RL), which builds a supervised transition model with logging dataset to avoid costly interactions with the online environment, has been a promising approach for offline policy optimization. As the discrepancy between the logging data and online environment may result in a distributional shift problem, many prior works have studied how to build robust transition models conservatively and estimate the model uncertainty accurately. However, the over-conservatism can limit the exploration of the agent, and the uncertainty estimates may be unreliable. In this work, we propose a novel Model-based Offline policy optimization framework with Adversarial Network (MOAN). The key idea is to use adversarial learning to build a transition model with better generalization, where an adversary is introduced to distinguish between in-distribution and out-of-distribution samples. Moreover, the adversary can naturally provide a quantification of the model's uncertainty with theoretical guarantees. Extensive experiments showed that our approach outperforms existing state-of-the-art baselines on widely studied offline RL benchmarks. It can also generate diverse in-distribution samples, and quantify the uncertainty more accurately.