Beyond Reward: Offline Preference-guided Policy Optimization

Yachen Kang, Diyuan Shi, Jinxin Liu, Li He, Donglin Wang

Keywords: offline reinforcement learning, preference-based reinforcement learning, hindsight information matching, preference-guided policy optimization

Abstract: In this work, we study offline preference-based reinforcement learning (PbRL), which relaxes the two fundamental supervisory signals in standard reinforcement learning (online accessible transition dynamics and rewards). In other words, the agent is provided with fixed offline trajectory transitions and human preferences between pairs of trajectories. Due to the orthogonality property of rewards and dynamics, one common practice is combining prior PbRL-based reward learning objectives with off-the-shelf offline RL algorithms to bridge preference modeling and offline learning. However, such two isolated optimizations require learning a separate reward function and thus place an information bottleneck on reward learning (the bridge). As an alternative, we propose offline preference-guided policy optimization (OPPO), an end-to-end offline PbRL formulation, which jointly learns to model the preference (for finding the optimal task policy) and the offline data (for eliminating OOD). In particular, OPPO introduces an offline hindsight information matching objective and a preference modeling objective. Then, iterating the two objectives over, we can directly extract a well-performing decision policy, avoiding a separate reward learning. We empirically show that OPPO can effectively model the offline preference and outperform prior competing baselines (including the offline RL algorithms performed over the true reward function).

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Reinforcement Learning (eg, decision and control, planning, hierarchical RL, robotics)

TL;DR: We propose an end-to-end offline preference-based reinforcement learning formulation that directly optimizes the policy by preference supervision without learning a separate reward function.

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2305.16217/code)