Reward Learning from Multiple Feedback Types

TL;DR

This paper explores learning reward models from multiple types of human feedback, demonstrating that diverse feedback sources can improve reward learning and downstream reinforcement learning performance.

Contribution

It introduces a framework for generating and utilizing six different feedback types, advancing reward learning beyond preference-based feedback.

Findings

Diverse feedback types enhance reward modeling accuracy.

Multi-type feedback improves RL performance compared to preference-only baselines.

Empirical evidence supports the potential of multi-source feedback in RLHF.

Abstract

Learning rewards from preference feedback has become an important tool in the alignment of agentic models. Preference-based feedback, often implemented as a binary comparison between multiple completions, is an established method to acquire large-scale human feedback. However, human feedback in other contexts is often much more diverse. Such diverse feedback can better support the goals of a human annotator, and the simultaneous use of multiple sources might be mutually informative for the learning process or carry type-dependent biases for the reward learning process. Despite these potential benefits, learning from different feedback types has yet to be explored extensively. In this paper, we bridge this gap by enabling experimentation and evaluating multi-type feedback in a broad set of environments. We present a process to generate high-quality simulated feedback of six different types. Then, we implement reward models and downstream RL training for all six feedback types. Based on the simulated feedback, we investigate the use of types of feedback across ten RL environments and compare them to pure preference-based baselines. We show empirically that diverse types of feedback can be utilized and lead to strong reward modeling performance. This work is the first strong indicator of the potential of multi-type feedback for RLHF.