# Latent dynamics models and model-based RL Area: [World models](https://mlsanity.com/wm/index.md). HTML: https://mlsanity.com/wm/latent-dynamics-models-and-model-based-rl/ ## Key facts - Latent dynamics models and model-based RL: 298 papers on arXiv since 2015 (data through 14 Oct 2026). - 153 of its 298 mapped papers (51%) cite “Dream to Control: Learning Behaviors by Latent Imagination” (2019, arXiv 1912.01603). - 129 of its 298 mapped papers (43%) cite “Mastering Atari with Discrete World Models” (2020, arXiv 2010.02193). - 30 new papers 17 Sep–14 Oct. ## Most cited here - [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019), cited by 153 papers here - [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020), cited by 129 papers here - [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023), cited by 115 papers here - [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018), cited by 83 papers here - [World Models](https://mlsanity.com/paper/1803.10122/) (2018), cited by 77 papers here - [When to Trust Your Model: Model-Based Policy Optimization](https://mlsanity.com/paper/1906.08253/) (2019), cited by 64 papers here - [Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models](https://mlsanity.com/paper/1805.12114/) (2018), cited by 62 papers here - [Transformers are Sample-Efficient World Models](https://mlsanity.com/paper/2209.00588/) (2022), cited by 61 papers here - [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023), cited by 55 papers here - [Planning to Explore via Self-Supervised World Models](https://mlsanity.com/paper/2005.05960/) (2020), cited by 47 papers here ## New (17 Sep–14 Oct) - [Back on Track: Deployment-time Policy Improvement via World Model Planning](https://mlsanity.com/paper/2610.19579/) (2026-10-14) - [ObsSpec: Accelerating Agentic Reinforcement Learning with Observation Speculation](https://mlsanity.com/paper/2610.15246/) (2026-10-11) - [CFG-Policy: Unified Diffusion Policy Learning Framework via Classifier-free Guidance](https://mlsanity.com/paper/2610.14936/) (2026-10-10) - [MHWA: Multi-timescale Hierarchical World-Action Model](https://mlsanity.com/paper/2610.14727/) (2026-10-10) - [Visualizing the World Model in an Agent's Value Function](https://mlsanity.com/paper/2610.14186/) (2026-10-09) - [Dream to Remember: Continual Steering of Generalist Robot Policies with World Models](https://mlsanity.com/paper/2610.13816/) (2026-10-09) - [Beyond Temporal Proximity: Explanatory World Models for Credit Assignment in Reinforcement Learning](https://mlsanity.com/paper/2610.13504/) (2026-10-09) - [World-Model Policy Arbiter for Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2610.10932/) (2026-10-07) - [RIWANav: Recursive World-Action Models with Self-Improvement for Urban Navigation](https://mlsanity.com/paper/2610.08640/) (2026-10-06) - [Learning in Dreams, Winning in Reality: A Continuous Dyna Loop for a Ten-Hero MOBA](https://mlsanity.com/paper/2610.08033/) (2026-10-06) - [Independent Multi-Agent Reinforcement Learning with Counterfactual Semantic-Social World Models](https://mlsanity.com/paper/2610.07704/) (2026-10-06) - [Considering Context: When World Models Need Context Encoders](https://mlsanity.com/paper/2610.06651/) (2026-10-05) - [Action-Consequence Alignment for Reliable Planning and Self-Improving in Latent World Models](https://mlsanity.com/paper/2610.04539/) (2026-10-03) - [DreamTest: World-Model Surrogates for Search-Based Testing of Deep Reinforcement Learning Agents](https://mlsanity.com/paper/2610.04494/) (2026-10-03) - [Network World Models as Environments for Algorithm Design on Complex Systems](https://mlsanity.com/paper/2610.01048/) (2026-10-01) - [Calibration-risk routing for controlled world-model adaptation](https://mlsanity.com/paper/2610.01001/) (2026-10-01) - [DashVMC: Real-Time Discrete World Model Control in Geometry Dash](https://mlsanity.com/paper/2609.40003/) (2026-09-30) - [Beyond Policy Alignment: Closing the Planning-Learning Loop for Robot Control with Learned World Models](https://mlsanity.com/paper/2609.39751/) (2026-09-30) - [Linear Recurrent Memory Suffices to Distil a World-Model Policy for Robot Air Hockey](https://mlsanity.com/paper/2609.39151/) (2026-09-30) - [Beyond Prediction: Steering VLM Agents with Retrospective World Modeling](https://mlsanity.com/paper/2609.39101/) (2026-09-30) - [Code to Control: Synthesizing Parameterized Reactive Controllers](https://mlsanity.com/paper/2609.38733/) (2026-09-30) - [Think Fast, Plan Selectively: Adaptive Deliberation for Efficient Data-Driven MPC](https://mlsanity.com/paper/2609.32591/) (2026-09-30) - [MA-JEPA: Joint-Embedding World Models for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2609.33563/) (2026-09-27) - [Beyond Conservatism: Recoverability-Conditioned Exploration for Model-Based Imitation Learning](https://mlsanity.com/paper/2609.33336/) (2026-09-27) - [Does Learning to Predict the World Help Agents Act? Auditing World-Model Post-Training](https://mlsanity.com/paper/2609.33335/) (2026-09-27) - [SwingRL: Adaptive Observation Reinforcement Learning with World-Model Prediction for Cable-Suspended Hoisting Control](https://mlsanity.com/paper/2609.33053/) (2026-09-27) - [MA-WAM: Multi-Agent World-Action Model for Test-Time Planning](https://mlsanity.com/paper/2609.31281/) (2026-09-25) - [Recommendation World Models for Future-State Control](https://mlsanity.com/paper/2609.30711/) (2026-09-25) - [Prioritized Rollouts for Efficient World Model-based Vision-Language-Action Policy Optimization](https://mlsanity.com/paper/2609.22879/) (2026-09-19) - [Adaptive Rollout Truncation Based on Epistemic Uncertainty for Efficient Offline World Model Training](https://mlsanity.com/paper/2609.21482/) (2026-09-18)