Adaptive World Models: Learning Behaviors by Latent Imagination Under Non-Stationarity

Emiliyan Gospodinov, Vaisakh Shaj, Philipp Becker, Stefan Geyer, Gerhard Neumann

Keywords: non-stationary model-based reinforcement learning, adaptive learning, multitask learning

TL;DR: Adaptive Model-based RL in Latent Spaces Under Non-Stationarity

Abstract: Developing foundational world models is a key research direction for embodied intelligence, with the ability to adapt to non-stationary environments being a crucial criterion. In this work, we introduce a new formalism, Hidden Parameter-POMDP, designed for control with adaptive world models. We demonstrate that this approach enables learning robust behaviors across a variety of non-stationary RL benchmarks. Additionally, this formalism effectively learns task abstractions in an unsupervised manner, resulting in structured, task-aware latent spaces.

Submission Number: 154