# Embodied Lifelong Learning for Task and Motion Planning

arXiv: https://arxiv.org/abs/2307.06870 · HTML: https://mlsanity.com/paper/2307.06870/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 34 references that are in the map.
- First posted on arXiv 13 Jul 2023.

## Builds on (most cited first, 24 of 24)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Overcoming catastrophic forgetting with hard attention to the task](https://mlsanity.com/paper/1801.01423/) (2018)
- [Variational Continual Learning](https://mlsanity.com/paper/1710.10628/) (2017)
- [Integrated Task and Motion Planning](https://mlsanity.com/paper/2010.01083/) (2020)
- [BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments](https://mlsanity.com/paper/2108.03332/) (2021)
- [A Deep Hierarchical Approach to Lifelong Learning in Minecraft](https://mlsanity.com/paper/1604.07255/) (2016)
- [Efficient Continual Learning with Modular Networks and Task-Driven Priors](https://mlsanity.com/paper/2012.12631/) (2020)
- [Continual Learning via Local Module Composition](https://mlsanity.com/paper/2111.07736/) (2021)
- [Learning Symbolic Operators for Task and Motion Planning](https://mlsanity.com/paper/2103.00589/) (2021)
- [Learning Neuro-Symbolic Skills for Bilevel Planning](https://mlsanity.com/paper/2206.10680/) (2022)
- [Predicate Invention for Bilevel Planning](https://mlsanity.com/paper/2203.09634/) (2022)
- [Learning compositional models of robot skills for task and motion planning](https://mlsanity.com/paper/2006.06444/) (2020)
- [Learning Neuro-Symbolic Relational Transition Models for Bilevel Planning](https://mlsanity.com/paper/2105.14074/) (2021)
- [Modular Lifelong Reinforcement Learning via Neural Composition](https://mlsanity.com/paper/2207.00429/) (2022)
- [Lifelong Learning of Compositional Structures](https://mlsanity.com/paper/2007.07732/) (2020)
- [Active model learning and diverse action sampling for task and motion planning](https://mlsanity.com/paper/1803.00967/) (2018)
- [How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition](https://mlsanity.com/paper/2207.07730/) (2022)
- [Discovering State and Action Abstractions for Generalized Task and Motion Planning](https://mlsanity.com/paper/2109.11082/) (2021)
- [Representation, learning, and planning algorithms for geometric task and motion planning](https://mlsanity.com/paper/2203.04605/) (2022)
- [Learning Sampling Dictionaries for Efficient and Generalizable Robot Motion Planning with Transformers](https://mlsanity.com/paper/2306.00851/) (2023)

## Built on by (most cited first, 17 of 17)

- [Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learning](https://mlsanity.com/paper/2407.01531/) (2024)
- [Diffusion Models for Robotic Manipulation: A Survey](https://mlsanity.com/paper/2504.08438/) (2025)
- [MaestroMotif: Skill Design from Artificial Intelligence Feedback](https://mlsanity.com/paper/2412.08542/) (2024)
- [Practice Makes Perfect: Planning to Learn Skill Parameter Policies](https://mlsanity.com/paper/2402.15025/) (2024)
- [A Survey of Continual Reinforcement Learning](https://mlsanity.com/paper/2506.21872/) (2025)
- [Neural Brain: A Neuroscience-inspired Framework for Embodied Agents](https://mlsanity.com/paper/2505.07634/) (2025)
- [EfficientLLaVA:Generalizable Auto-Pruning for Large Vision-language Models](https://mlsanity.com/paper/2503.15369/) (2025)
- [Reconstruct before Query: Continual Missing Modality Learning with Decomposed Prompt Collaboration](https://mlsanity.com/paper/2403.11373/) (2024)
- [Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges](https://mlsanity.com/paper/2512.04770/) (2025)
- [Kintsugi: Learning Policies by Repairing Executable Knowledge Bases](https://mlsanity.com/paper/2605.09487/) (2026)
- [CLIMB: Language-Guided Continual Learning for Task Planning with Iterative Model Building](https://mlsanity.com/paper/2410.13756/) (2024)
- [Learning to Bridge the Gap: Efficient Novelty Recovery with Planning and Reinforcement Learning](https://mlsanity.com/paper/2409.19226/) (2024)
- [Task-agnostic Lifelong Robot Learning with Retrieval-based Weighted Local Adaptation](https://mlsanity.com/paper/2410.02995/) (2024)
- [Coloring Between the Lines: Personalization in the Null Space of Planning Constraints](https://mlsanity.com/paper/2505.15503/) (2025)
- [Lifelong In-Context Learning with Transformers Requires Parametric Forms of Attention](https://mlsanity.com/paper/2606.25342/) (2026)
- [Adapting Actively on the Fly: Relevance-Guided Online Meta-Learning with Latent Concepts for Geospatial Discovery](https://mlsanity.com/paper/2602.17605/) (2026)
- [Learning Bilevel Policies over Symbolic World Models for Long-Horizon Planning](https://mlsanity.com/paper/2605.15975/) (2026)

## Abstract (arXiv)

A robot deployed in a home over long stretches of time faces a true lifelong learning problem. As it seeks to provide assistance to its users, the robot should leverage any accumulated experience to improve its own knowledge and proficiency. We formalize this setting with a novel formulation of lifelong learning for task and motion planning (TAMP), which endows our learner with the compositionality of TAMP systems. Exploiting the modularity of TAMP, we develop a mixture of generative models that produces candidate continuous parameters for a planner. Whereas most existing lifelong learning approaches determine a priori how data is shared across various models, our approach learns shared and non-shared models and determines which to use online during planning based on auxiliary tasks that serve as a proxy for each model's understanding of a state. Our method exhibits substantial improvements (over time and compared to baselines) in planning success on 2D and BEHAVIOR domains.