2026
Mind Dreamer: Untethering Imagination via Active Counterfactual Reasoning on Latent Manifolds
ICML 2026poster
Model-Based Reinforcement Learning (MBRL) leverages latent imagination for sample efficiency, yet remains constrained by **Historical Tethering**: imagination is typically initialized from observed states. This creates a learning asymmetry, where the world model’s manifold discovery outpaces the pol…