ConTraIRL: Factorized Contrastive Abstractions for Transferable IRL 事件

ConTraIRL: Factorized Contrastive Abstractions for Transferable IRL arXiv:2606.03017v1 Announce Type: cross Abstract: Reward transfer in Inverse Reinforcement Learning (IRL) is unreliable when policies must generalize to unseen combinations of environment dynamics and task goals. We propose Factorized Contrastive Abstractions for Transferable IRL (ConTraIRL), a framework that enables compositional reward transfer by learning decoupled latent representations of these two factors. ConTraIRL uses