Non-Markovian reward modelling from trajectory labels via Interpretable multiple instance learning

Early, Joseph, Bewley, Tom, Evers, Christine and Ramchurn, Sarvapali (2022) Non-Markovian reward modelling from trajectory labels via Interpretable multiple instance learning. Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K. and Oh, A. (eds.) In Advances in Neural Information Processing Systems 35 - 36th Conference on Neural Information Processing Systems, NeurIPS 2022. vol. 35, Neural Information Processing Systems Foundation. 12 pp .

Abstract

We generalise the problem of reward modelling (RM) for reinforcement learning (RL) to handle non-Markovian rewards. Existing work assumes that human evaluators observe each step in a trajectory independently when providing feedback on agent behaviour. In this work, we remove this assumption, extending RM to capture temporal dependencies in human assessment of trajectories. We show how RM can be approached as a multiple instance learning (MIL) problem, where trajectories are treated as bags with return labels, and steps within the trajectories are instances with unseen reward labels. We go on to develop new MIL models that are able to capture the time dependencies in labelled trajectories. We demonstrate on a range of RL tasks that our novel MIL models can reconstruct reward functions to a high level of accuracy, and can be used to train high-performing agent policies.

This record has no associated files available for download.

Contributors

Author: Joseph Early

Author: Christine Evers

Author: Sarvapali Ramchurn

Download statistics