mlsanityData to 7 Oct 2026

Learning Neuro-Symbolic Relational Transition Models for Bilevel Planning

arXiv 2105.14074 ↗First posted 28 May 2021cs.AI cs.LG cs.ROcited by 43

Not on the map. Why?

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

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). Builds on 38 of its 75 references that are in the map. First posted on arXiv 28 May 2021.

Builds on

38 of 75 references.

References · 38

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,873
  3. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,598
  4. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  5. 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
  6. 2020Mastering Atari with Discrete World Modelscited by 990
  7. 2017AI2-THOR: An Interactive 3D Environment for Visual AIcited by 850
  8. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 748
  9. 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 503
  10. 2017Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuningcited by 288
  11. 2020Integrated Task and Motion Planningcited by 281
  12. 2020Accelerating Reinforcement Learning with Learned Skill Priorscited by 220
26 more
  1. 2020OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learningcited by 164
  2. 2020Parrot: Data-Driven Behavioral Priors for Reinforcement Learningcited by 136
  3. 2016A Compositional Object-Based Approach to Learning Physical Dynamicscited by 119
  4. 2018SDRL: Interpretable and Data-efficient Deep Reinforcement Learning Leveraging Symbolic Planningcited by 77
  5. 2019Online Replanning in Belief Space for Partially Observable Task and Motion Problemscited by 60
  6. 2020Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictorscited by 60
  7. 2017Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundarycited by 58
  8. 2017Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physicscited by 57
  9. 2020On the role of planning in model-based deep reinforcement learningcited by 57
  10. 2021Learning Symbolic Operators for Task and Motion Planningcited by 57
  11. 2018PEORL: Integrating Symbolic Planning and Hierarchical Reinforcement Learning for Robust Decision-Makingcited by 51
  12. 2020Learning compositional models of robot skills for task and motion planningcited by 47
  13. 2020Deep Visual Reasoning: Learning to Predict Action Sequences for Task and Motion Planning from an Initial Scene Imagecited by 45
  14. 2020Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networkscited by 38
  15. 2018Learning Features and Abstract Actions for Computing Generalized Planscited by 35
  16. 2020Generalized Planning With Deep Reinforcement Learningcited by 35
  17. 2017Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learningcited by 27
  18. 2020Broadly-Exploring, Local-Policy Trees for Long-Horizon Task Planningcited by 26
  19. 2019Unsupervised Grounding of Plannable First-Order Logic Representation from Imagescited by 24
  20. 2020Understanding the Power and Limitations of Teaching with Imperfect Knowledgecited by 23
  21. 2020SPOTTER: Extending Symbolic Planning Operators through Targeted Reinforcement Learningcited by 23
  22. 2018Composable Planning with Attributescited by 21
  23. 2020Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planningcited by 19
  24. 2018Learning sparse relational transition modelscited by 11
  25. 2020Planning from Pixels in Atari with Learned Symbolic Representationscited by 11
  26. 2019What Should I Do Now? Marrying Reinforcement Learning and Symbolic Planningcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 7; 2023: 10; 2024: 9; 2025: 8; 2026: 8.

43 papers.

Sort:

By area:

  1. 2022ProcTHOR: Large-Scale Embodied AI Using Procedural Generationcited by 369
  2. 2023Text2Motion: From Natural Language Instructions to Feasible Planscited by 223
  3. 2022Learning Neuro-Symbolic Skills for Bilevel Planningcited by 55
  4. 2022Predicate Invention for Bilevel Planningcited by 49
  5. 2024VisualPredicator: Learning Abstract World Models with Neuro-Symbolic Predicates for Robot Planningcited by 37
  6. 2025Neuro-Symbolic AI in 2024: A Systematic Reviewcited by 36
  7. 2022LEAGUE: Guided Skill Learning and Abstraction for Long-Horizon Manipulationcited by 32
  8. 2024A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approachescited by 19
  9. 2024Trust the PRoC3S: Solving Long-Horizon Robotics Problems with LLMs and Constraint Satisfactioncited by 19
  10. 2022Learning Efficient Abstract Planning Models that Choose What to Predictcited by 17
  11. 2023Embodied Lifelong Learning for Task and Motion Planningcited by 17
  12. 2024Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot Autonomycited by 16
31 more
  1. 2023Primitive Skill-based Robot Learning from Human Evaluative Feedbackcited by 15
  2. 2021Trajectory Prediction with Linguistic Representationscited by 13
  3. 2022Goal-Space Planning with Subgoal Modelscited by 12
  4. 2024From Pixels to Predicates: Learning Symbolic World Models via Pretrained Vision-Language Modelscited by 11
  5. 2023Embodied Active Learning of Relational State Abstractions for Bilevel Planningcited by 8
  6. 2023NOIR: Neural Signal Operated Intelligent Robots for Everyday Activitiescited by 8
  7. 2024LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulationcited by 8
  8. 2025ExoPredicator: Learning Abstract Models of Dynamic Worlds for Robot Planningcited by 8
  9. 2023PDSketch: Integrated Planning Domain Programming and Learningcited by 7
  10. 2023Egocentric Planning for Scalable Embodied Task Achievementcited by 7
  11. 2023Robot Task Planning Based on Large Language Model Representing Knowledge with Directed Graph Structurescited by 7
  12. 2025Neuro-Symbolic Imitation Learning: Discovering Symbolic Abstractions for Skill Learningcited by 4
  13. 2022Learning Temporally Extended Skills in Continuous Domains as Symbolic Actions for Planningcited by 3
  14. 2023Discovering Predictive Relational Object Symbols with Symbolic Attentive Layerscited by 3
  15. 2024Learning Planning Abstractions from Languagecited by 3
  16. 2025Curiosity-Driven Imagination: Discovering Plan Operators and Learning Associated Policies for Open-World Adaptationcited by 3
  17. 2025SLAP: Shortcut Learning for Abstract Planningcited by 3
  18. 2026Kintsugi: Learning Policies by Repairing Executable Knowledge Basescited by 3
  19. 2023Learning Type-Generalized Actions for Symbolic Planningcited by 2
  20. 2025Few-Shot Neuro-Symbolic Imitation Learning for Long-Horizon Planning and Actingcited by 2
  21. 2025Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunitiescited by 2
  22. 2026Learning Lifted Action Models from Unsupervised Visual Tracescited by 2
  23. 2024Neuro-Symbolic Skill Discovery for Conditional Multi-Level Planningcited by 1
  24. 2024A New View on Planning in Online Reinforcement Learningcited by 0
  25. 2025NOIR 2.0: Neural Signal Operated Intelligent Robots for Everyday Activitiescited by 0
  26. 2026Build on Priors: Vision--Language--Guided Neuro-Symbolic Imitation Learning for Data-Efficient Real-World Robot Manipulationcited by 0
  27. 2026Learning Bilevel Policies over Symbolic World Models for Long-Horizon Planningcited by 0
  28. 2026Neuro-Symbolic Learning for Long-Horizon Task Planning Under Complex Logical Constraintscited by 0
  29. 2026NeSy-CSA: A Neuro-Symbolic Framework for Open-Ended Critical Scenario Attributioncited by 0
  30. 2026Learning Action Models with Conditional and Quantified Effects via Uncertainty-Guided Explorationcited by 0
  31. 2026EMPIRIC: Experiment-Driven Learning of Residual World Models for Robot Planningcited by 0