Foundational

• World Models — Ha & Schmidhuber, NeurIPS 2018 https://arxiv.org/abs/1803.10122
• Learning Latent Dynamics for Planning from Pixels (PlaNet) — Hafner et al., ICML 2019 https://arxiv.org/abs/1811.04551
• Dream to Control: Learning Behaviors by Latent Imagination (DreamerV1) — Hafner et al., ICLR 2020 https://arxiv.org/abs/1912.01603
• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm (AlphaZero) — Silver et al., Science 2018 https://arxiv.org/abs/1712.01815

Core MBRL

• Mastering Atari with Discrete World Models (DreamerV2) — Hafner et al., ICLR 2021 https://arxiv.org/abs/2010.02193
• Mastering Diverse Control Tasks through World Models (DreamerV3) — Hafner et al., Nature 2023/2025 https://arxiv.org/abs/2301.04104
• Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model (MuZero) — Schrittwieser et al., Nature 2020 https://arxiv.org/abs/1911.08265
• Temporal Difference Learning for Model Predictive Control (TD-MPC2) — Hansen et al., ICML 2024 https://arxiv.org/abs/2310.16828
• Transformers are Sample-Efficient World Models (IRIS) — Micheli et al., ICLR 2023 https://arxiv.org/abs/2209.00588

Frontier (2023–2025)

• V-JEPA: Revisiting Feature Prediction for Learning Visual Representations from Video — Bardes et al., NeurIPS 2024 https://arxiv.org/abs/2404.08471
• GAIA-1: A Generative World Model for Autonomous Driving — Hu et al., arXiv 2023 https://arxiv.org/abs/2309.17080
• Genie: Generative Interactive Environments — Bruce et al., ICML 2024 https://arxiv.org/abs/2402.15391
• Cosmos: World Foundation Model Platform for Physical AI — NVIDIA, 2025 https://arxiv.org/abs/2501.03575

Worth Exploring

• A Path Towards Autonomous Machine Intelligence — LeCun, OpenReview 2022 https://openreview.net/forum?id=BZ5a1r-kVsf
• Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture (I-JEPA) — Assran et al., CVPR 2023 https://arxiv.org/abs/2301.08243
• DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning — Zhou et al., arXiv 2024 https://arxiv.org/abs/2411.04983
• Recurrent Experience Replay in Distributed Reinforcement Learning (R2D2) — Kapturowski et al., ICLR 2019 https://openreview.net/forum?id=r1lyTjAqYX