Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning

ArXi:2605.09364v1 Announce Type: new This paper investigates robust representation learning in offline goal-conditioned reinforcement learning (GCRL). Particularly in sparse reward scenarios, learning representations that align state and goal latents is a challenge that frequently culminates in representation divergence where the encoder drifts toward a low-dimensional, goal-agnostic subspace that destabilizes policy learning.