latent dynamics model

Local Motion Matters: A Deconstruct-Recompose Paradigm for Reinforcement Learning Pre-training from Videos CVPR 2026 VideoWorld 2: Learning Transferable Knowledge from Real-world Videos CVPR 2026 A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning AISTATS 2025 Reward-free World Models for Online Imitation Learning ICML 2025 VideoWorld: Exploring Knowledge Learning from Unlabeled Videos CVPR 2025 Bi-Level Motion Imitation for Humanoid Robots CoRL 2024 Efficient Monte Carlo Tree Search via On-the-Fly State-Conditioned Action Abstraction UAI 2024 State-wise safe reinforcement learning with pixel observations L4DC 2024 Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning NeurIPS 2023 Simplified Temporal Consistency Reinforcement Learning ICML 2023 Learning Multi-Object Dynamics with Compositional Neural Radiance Fields CoRL 2022 Learning Robust Dynamics through Variational Sparse Gating NeurIPS 2022 Temporal Difference Learning for Model Predictive Control ICML 2022 Model-Based Reinforcement Learning via Imagination with Derived Memory NeurIPS 2021 Learning Predictive Representations for Deformable Objects Using Contrastive Estimation CoRL 2020 Planning from Images with Deep Latent Gaussian Process Dynamics L4DC 2020 Imagined Value Gradients: Model-Based Policy Optimization with Tranferable Latent Dynamics Models CoRL 2019