<ul><li>MOBODY is a Model-Based Off-Dynamics offline RL algorithm designed to address the limitations of existing off-dynamics offline RL methods.</li><li>It enables exploration of the target domain by generating synthetic transitions through model rollouts for data augmentation during offline policy learning.</li><li>MOBODY learns target dynamics using representation learning that discovers a shared latent representation of states and transitions across domains.</li><li>Evaluation on MuJoCo benchmarks shows that MOBODY outperforms state-of-the-art baselines, particularly in challenging scenarios.</li></ul>

MOBODY: Model Based Off-Dynamics Offline Reinforcement Learning

Discover more