# Broadly-Exploring, Local-Policy Trees for Long-Horizon Task Planning

arXiv: https://arxiv.org/abs/2010.06491 · HTML: https://mlsanity.com/paper/2010.06491/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Oct 2020.

## Built on by (most cited first, 26 of 26)

- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Contrastive Learning as Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2206.07568/) (2022)
- [Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning](https://mlsanity.com/paper/2311.17842/) (2023)
- [Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills](https://mlsanity.com/paper/2104.07749/) (2021)
- [Rapid Exploration for Open-World Navigation with Latent Goal Models](https://mlsanity.com/paper/2104.05859/) (2021)
- [Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation](https://mlsanity.com/paper/2109.01115/) (2021)
- [Latent Plans for Task-Agnostic Offline Reinforcement Learning](https://mlsanity.com/paper/2209.08959/) (2022)
- [Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agents](https://mlsanity.com/paper/2303.00855/) (2023)
- [LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied Agents](https://mlsanity.com/paper/2402.08178/) (2024)
- [Learning Neuro-Symbolic Relational Transition Models for Bilevel Planning](https://mlsanity.com/paper/2105.14074/) (2021)
- [Hierarchical Planning with Latent World Models](https://mlsanity.com/paper/2604.03208/) (2026)
- [IFOR: Iterative Flow Minimization for Robotic Object Rearrangement](https://mlsanity.com/paper/2202.00732/) (2022)
- [NeRP: Neural Rearrangement Planning for Unknown Objects](https://mlsanity.com/paper/2106.01352/) (2021)
- [Affordance Learning from Play for Sample-Efficient Policy Learning](https://mlsanity.com/paper/2203.00352/) (2022)
- [Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning](https://mlsanity.com/paper/2111.03189/) (2021)
- [Generating Executable Action Plans with Environmentally-Aware Language Models](https://mlsanity.com/paper/2210.04964/) (2022)
- [Neural MP: A Generalist Neural Motion Planner](https://mlsanity.com/paper/2409.05864/) (2024)
- [Example-Driven Model-Based Reinforcement Learning for Solving Long-Horizon Visuomotor Tasks](https://mlsanity.com/paper/2109.10312/) (2021)
- [Learning Robotic Navigation from Experience: Principles, Methods, and Recent Results](https://mlsanity.com/paper/2212.06759/) (2022)
- [Deep Reactive Policy: Learning Reactive Manipulator Motion Planning for Dynamic Environments](https://mlsanity.com/paper/2509.06953/) (2025)
- [A Survey on the Integration of Machine Learning with Sampling-based Motion Planning](https://mlsanity.com/paper/2211.08368/) (2022)
- [Leveraging Jumpy Models for Planning and Fast Learning in Robotic Domains](https://mlsanity.com/paper/2302.12617/) (2023)
- [Enabling Visual Action Planning for Object Manipulation through Latent Space Roadmap](https://mlsanity.com/paper/2103.02554/) (2021)
- [Train-Once Plan-Anywhere Kinodynamic Motion Planning via Diffusion Trees](https://mlsanity.com/paper/2508.21001/) (2025)
- [A Simple Approach to Continual Learning by Transferring Skill Parameters](https://mlsanity.com/paper/2110.10255/) (2021)
- [Efficient Learning of High Level Plans from Play](https://mlsanity.com/paper/2303.09628/) (2023)

## Abstract (arXiv)

Long-horizon planning in realistic environments requires the ability to reason over sequential tasks in high-dimensional state spaces with complex dynamics. Classical motion planning algorithms, such as rapidly-exploring random trees, are capable of efficiently exploring large state spaces and computing long-horizon, sequential plans. However, these algorithms are generally challenged with complex, stochastic, and high-dimensional state spaces as well as in the presence of narrow passages, which naturally emerge in tasks that interact with the environment. Machine learning offers a promising solution for its ability to learn general policies that can handle complex interactions and high-dimensional observations. However, these policies are generally limited in horizon length. Our approach, Broadly-Exploring, Local-policy Trees (BELT), merges these two approaches to leverage the strengths of both through a task-conditioned, model-based tree search. BELT uses an RRT-inspired tree search to efficiently explore the state space. Locally, the exploration is guided by a task-conditioned, learned policy capable of performing general short-horizon tasks. This task space can be quite general and abstract; its only requirements are to be sampleable and to well-cover the space of useful tasks. This search is aided by a task-conditioned model that temporally extends dynamics propagation to allow long-horizon search and sequential reasoning over tasks. BELT is demonstrated experimentally to be able to plan long-horizon, sequential trajectories with a goal conditioned policy and generate plans that are robust.