Preprint
Aug 2026
Observation-Grounded Self-Predictive Reinforcement Learning for Visual Continuous Control
Observation-Grounded Self-Predictive Representations (OG-SPR), a model-free visual RL algorithm for continuous control that learns representations that are both temporally predictive in latent space and grounded in observation-level dynamics, is proposed.
Xinwei Liu, Junyuan Liang, Jianting Zhang et al.
· 0 citations