# Learning Neuro-Symbolic Relational Transition Models for Bilevel Planning

arXiv: https://arxiv.org/abs/2105.14074 · HTML: https://mlsanity.com/paper/2105.14074/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 75 references that are in the map.
- First posted on arXiv 28 May 2021.

## Builds on (most cited first, 30 of 38)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [AI2-THOR: An Interactive 3D Environment for Visual AI](https://mlsanity.com/paper/1712.05474/) (2017)
- [Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models](https://mlsanity.com/paper/1805.12114/) (2018)
- [Interaction Networks for Learning about Objects, Relations and Physics](https://mlsanity.com/paper/1612.00222/) (2016)
- [Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning](https://mlsanity.com/paper/1708.02596/) (2017)
- [Integrated Task and Motion Planning](https://mlsanity.com/paper/2010.01083/) (2020)
- [Accelerating Reinforcement Learning with Learned Skill Priors](https://mlsanity.com/paper/2010.11944/) (2020)
- [OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning](https://mlsanity.com/paper/2010.13611/) (2020)
- [Parrot: Data-Driven Behavioral Priors for Reinforcement Learning](https://mlsanity.com/paper/2011.10024/) (2020)
- [A Compositional Object-Based Approach to Learning Physical Dynamics](https://mlsanity.com/paper/1612.00341/) (2016)
- [SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planning](https://mlsanity.com/paper/1811.00090/) (2018)
- [Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors](https://mlsanity.com/paper/2006.13205/) (2020)
- [Online Replanning in Belief Space for Partially Observable Task and Motion Problems](https://mlsanity.com/paper/1911.04577/) (2019)
- [Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundary](https://mlsanity.com/paper/1705.00154/) (2017)
- [Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics](https://mlsanity.com/paper/1706.04317/) (2017)
- [Learning Symbolic Operators for Task and Motion Planning](https://mlsanity.com/paper/2103.00589/) (2021)
- [On the role of planning in model-based deep reinforcement learning](https://mlsanity.com/paper/2011.04021/) (2020)
- [PEORL: Integrating Symbolic Planning and Hierarchical Reinforcement Learning for Robust Decision-Making](https://mlsanity.com/paper/1804.07779/) (2018)
- [Deep Visual Reasoning: Learning to Predict Action Sequences for Task and Motion Planning from an Initial Scene Image](https://mlsanity.com/paper/2006.05398/) (2020)
- [Learning compositional models of robot skills for task and motion planning](https://mlsanity.com/paper/2006.06444/) (2020)
- [Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks](https://mlsanity.com/paper/2009.05613/) (2020)
- [Learning Features and Abstract Actions for Computing Generalized Plans](https://mlsanity.com/paper/1811.07231/) (2018)
- [Generalized Planning With Deep Reinforcement Learning](https://mlsanity.com/paper/2005.02305/) (2020)
- [Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning](https://mlsanity.com/paper/1703.03078/) (2017)
- [Broadly-Exploring, Local-Policy Trees for Long-Horizon Task Planning](https://mlsanity.com/paper/2010.06491/) (2020)

## Built on by (most cited first, 30 of 43)

- [ProcTHOR: Large-Scale Embodied AI Using Procedural Generation](https://mlsanity.com/paper/2206.06994/) (2022)
- [Text2Motion: From Natural Language Instructions to Feasible Plans](https://mlsanity.com/paper/2303.12153/) (2023)
- [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)
- [VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planning](https://mlsanity.com/paper/2410.23156/) (2024)
- [Neuro-Symbolic AI in 2024: A Systematic Review](https://mlsanity.com/paper/2501.05435/) (2025)
- [LEAGUE: Guided Skill Learning and Abstraction for Long-Horizon Manipulation](https://mlsanity.com/paper/2210.12631/) (2022)
- [A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approaches](https://mlsanity.com/paper/2404.02817/) (2024)
- [Trust the PRoC3S: Solving Long-Horizon Robotics Problems with LLMs and Constraint Satisfaction](https://mlsanity.com/paper/2406.05572/) (2024)
- [Learning Efficient Abstract Planning Models that Choose What to Predict](https://mlsanity.com/paper/2208.07737/) (2022)
- [Embodied Lifelong Learning for Task and Motion Planning](https://mlsanity.com/paper/2307.06870/) (2023)
- [Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomy](https://mlsanity.com/paper/2406.16087/) (2024)
- [Primitive Skill-based Robot Learning from Human Evaluative Feedback](https://mlsanity.com/paper/2307.15801/) (2023)
- [Trajectory Prediction with Linguistic Representations](https://mlsanity.com/paper/2110.09741/) (2021)
- [Goal-Space Planning with Subgoal Models](https://mlsanity.com/paper/2206.02902/) (2022)
- [From Pixels to Predicates: Learning Symbolic World Models via Pretrained Vision-Language Models](https://mlsanity.com/paper/2501.00296/) (2024)
- [ExoPredicator: Learning Abstract Models of Dynamic Worlds for Robot Planning](https://mlsanity.com/paper/2509.26255/) (2025)
- [Embodied Active Learning of Relational State Abstractions for Bilevel Planning](https://mlsanity.com/paper/2303.04912/) (2023)
- [NOIR: Neural Signal Operated Intelligent Robots for Everyday Activities](https://mlsanity.com/paper/2311.01454/) (2023)
- [LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulation](https://mlsanity.com/paper/2411.00773/) (2024)
- [PDSketch: Integrated Planning Domain Programming and Learning](https://mlsanity.com/paper/2303.05501/) (2023)
- [Egocentric Planning for Scalable Embodied Task Achievement](https://mlsanity.com/paper/2306.01295/) (2023)
- [Robot Task Planning Based on Large Language Model Representing Knowledge with Directed Graph Structures](https://mlsanity.com/paper/2306.05171/) (2023)
- [Neuro-Symbolic Imitation Learning: Discovering Symbolic Abstractions for Skill Learning](https://mlsanity.com/paper/2503.21406/) (2025)
- [Learning Temporally Extended Skills in Continuous Domains as Symbolic Actions for Planning](https://mlsanity.com/paper/2207.05018/) (2022)
- [Discovering Predictive Relational Object Symbols with Symbolic Attentive Layers](https://mlsanity.com/paper/2309.00889/) (2023)
- [Learning Planning Abstractions from Language](https://mlsanity.com/paper/2405.03864/) (2024)
- [Curiosity-Driven Imagination: Discovering Plan Operators and Learning Associated Policies for Open-World Adaptation](https://mlsanity.com/paper/2503.04931/) (2025)
- [SLAP: Shortcut Learning for Abstract Planning](https://mlsanity.com/paper/2511.01107/) (2025)
- [Learning Lifted Action Models from Unsupervised Visual Traces](https://mlsanity.com/paper/2604.19043/) (2026)

## Abstract (arXiv)

In robotic domains, learning and planning are complicated by continuous state spaces, continuous action spaces, and long task horizons. In this work, we address these challenges with Neuro-Symbolic Relational Transition Models (NSRTs), a novel class of models that are data-efficient to learn, compatible with powerful robotic planning methods, and generalizable over objects. NSRTs have both symbolic and neural components, enabling a bilevel planning scheme where symbolic AI planning in an outer loop guides continuous planning with neural models in an inner loop. Experiments in four robotic planning domains show that NSRTs can be learned after only tens or hundreds of training episodes, and then used for fast planning in new tasks that require up to 60 actions and involve many more objects than were seen during training. Video: https://tinyurl.com/chitnis-nsrts