Self-supervised Hierarchical Visual Reasoning with World Model

ArXi:2605.17537v2 Announce Type: replace 3D open-world environments with adversarial opponents remain a core challenge for reinforcement learning due to their vast state spaces. Effective reasoning representations are essential in such settings. While existing self-supervised visual foresight reasoning approaches often suffer from multi-step error accumulation, many recent studies resort to injecting domain-specific knowledge for stable guidance.