# Dream and Search to Control: Latent Space Planning for Continuous Control

arXiv: https://arxiv.org/abs/2010.09832 · HTML: https://mlsanity.com/paper/2010.09832/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2020.

## Built on by (most cited first, 5 of 5)

- [Learning and Planning in Complex Action Spaces](https://mlsanity.com/paper/2104.06303/) (2021)
- [Hieros: Hierarchical Imagination on Structured State Space Sequence World Models](https://mlsanity.com/paper/2310.05167/) (2023)
- [Competence-Aware AI Agents with Metacognition for Unknown Situations and Environments (MUSE)](https://mlsanity.com/paper/2411.13537/) (2024)
- [Offline Policy Comparison with Confidence: Benchmarks and Baselines](https://mlsanity.com/paper/2205.10739/) (2022)
- [Why We Need World Models for AGI: Where LLMs Fail and How World Models May Outperform](https://mlsanity.com/paper/2605.23972/) (2026)

## Abstract (arXiv)

Learning and planning with latent space dynamics has been shown to be useful for sample efficiency in model-based reinforcement learning (MBRL) for discrete and continuous control tasks. In particular, recent work, for discrete action spaces, demonstrated the effectiveness of latent-space planning via Monte-Carlo Tree Search (MCTS) for bootstrapping MBRL during learning and at test time. However, the potential gains from latent-space tree search have not yet been demonstrated for environments with continuous action spaces. In this work, we propose and explore an MBRL approach for continuous action spaces based on tree-based planning over learned latent dynamics. We show that it is possible to demonstrate the types of bootstrapping benefits as previously shown for discrete spaces. In particular, the approach achieves improved sample efficiency and performance on a majority of challenging continuous-control benchmarks compared to the state-of-the-art.