cs.LGNov 2, 2026

Inferring Transferable Rewards via Active Inverse Reinforcement Learning

Authors: Victor Villin, Till Freihaut, Andreas Schlaginhaufen, Christos Dimitrakakis, Maryam Kamgarpour, Giorgia Ramponi

Organizations: University of Neuchˆatel · University of Zurich · EPFL

Abstract

Inverse Reinforcement Learning (IRL) aims to recover expert rewards that transfer across environments with differing dynamics. Prior work has shown that such transfer is possible when gathering expert demonstrations across sufficiently different dynamics. In practice, however, expert demonstrations are costly, making it critical to select the right dynamics to reduce the quantity of expert data required for learning transferable rewards. We propose a two-phase approach: we first cycle through the available dynamics to obtain a reliable reward estimate, then actively select dynamics to reduce our uncertainty about the expert reward. Crucially, this yields novel sample complexity guarantees on transfer that hold for any dynamics, with a rate independent of the number of available dynamics. Empirically, our method significantly reduces the number of expert demonstrations needed to learn a transferable reward.

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. ConTraIRL: Factorized Contrastive Abstractions for Transferable IRL

    Jun 2, 2026Yikang Gui, Bikramjit Banerjee, Prashant DoshiDisentangled Representation LearningReinforcement Learning

  2. Trust Region Inverse Reinforcement Learning: Explicit Dual Ascent using Local Policy Updates

    May 10, 2026Anish Diwan, Davide Tateo, Christopher E. Mower +3Reinforcement LearningPolicy Optimization

  3. Inverse Reinforcement Learning without an Optimal Demonstrator: A Feasible Reward Set Approach

    May 29, 2026Kihyun Kim, Shripad Deshmukh, Nikos Vlassis +1Reinforcement LearningLearning from Demonstration