NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
84 results for “keyword:"model based reinforcement learning"” in ICLR 2027. 22 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]BoundaryWorld: Decision-Regime-Sufficient World Models for Reliable Long-Horizon Planning▼4.5k2.67
[PDF]When Should a World Model Trust Its Imagination? Local Empirical Support Predicts Recursive Rollout Failure▲6.1k2.00
[PDF]FocusDreamer: Task-Directed Model-Based Reinforcement Learning Guided by Return Relevance▲5.4k3.00
[PDF]Disagreement in Imagination: A Cross-Timescale Consistency Signal for Robust Model-Based Control▼1.2k1.67
[PDF]A World Model Can Predict the Future Without Knowing Its Cause: Interventional Evaluation of Action-Conditioned World Models▲3.0k2.33
[PDF]Prioritized Rollouts for Efficient World Model-based Vision-Language-Action Policy Optimization▲3.0k2.33
[PDF]Beyond Static Graph World Models: Learning Stochastic Latent Dynamics over Evolving Topologies▲3.0k2.33
[PDF]Compositional Context Encoding for Out-of-Distribution Generalization in Modular World Models▼1361.33
Withdrawn or desk rejected (22)
[PDF]What Should I Try Next? Decision-Relevant Counterfactual Information Gain for Active World ModelsWithdrawn1.00
[PDF]ErrataWM: Correcting Frozen World Models with a Non-Parametric Memory of Their Own ErrorsWithdrawn2.00
[PDF]The Simulator Says Yes: Language World Models Narrate the Executions Their Environment RefusedDesk rejected