mlsanityData to 7 Oct 2026

PDSketch: Integrated Planning Domain Programming and Learning

arXiv 2303.05501 ↗First posted 9 Mar 2023cs.AI cs.LG cs.ROcited by 7

Not on the map. Why?

Abstract (arXiv)

This paper studies a model learning and online planning approach towards building flexible and general robots. Specifically, we investigate how to exploit the locality and sparsity structures in the underlying environmental transition model to improve model generalization, data-efficiency, and runtime-efficiency. We present a new domain definition language, named PDSketch. It allows users to flexibly define high-level structures in the transition models, such as object and feature dependencies, in a way similar to how programmers use TensorFlow or PyTorch to specify kernel sizes and hidden dimensions of a convolutional neural network. The details of the transition model will be filled in by trainable neural networks. Based on the defined structures and learned parameters, PDSketch automatically generates domain-independent planning heuristics without additional training. The derived heuristics accelerate the performance-time planning for novel goals.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 25 of its 72 references that are in the map. First posted on arXiv 9 Mar 2023.

Builds on

25 of 72 references.

References · 25

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2017Neural Discrete Representation Learningcited by 4,650
  4. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,528
  5. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  6. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
  7. 2020Mastering Atari with Discrete World Modelscited by 990
  8. 2020Learning Invariant Representations for Reinforcement Learning without Reconstructioncited by 424
  9. 2019Neural Probabilistic Logic Programming in DeepProbLogcited by 389
  10. 2020Transporter Networks: Rearranging the Visual World for Robotic Manipulationcited by 342
  11. 2020Integrated Task and Motion Planningcited by 281
  12. 2018PDDLStream: Integrating Symbolic Planners and Blackbox Samplers via Optimistic Adaptive Planningcited by 147
13 more
  1. 2019Planning with Goal-Conditioned Policiescited by 144
  2. 2020Logical Neural Networkscited by 118
  3. 2019Entity Abstraction in Visual Model-Based Reinforcement Learningcited by 110
  4. 2018Temporal Difference Models: Model-Free Deep RL for Model-Based Controlcited by 89
  5. 2017Recurrent Environment Simulatorscited by 68
  6. 2017Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physicscited by 57
  7. 2021Learning Symbolic Operators for Task and Motion Planningcited by 57
  8. 2021Learning Neuro-Symbolic Relational Transition Models for Bilevel Planningcited by 43
  9. 2019Learning First-Order Symbolic Representations for Planning from the Structure of the State Spacecited by 38
  10. 2019Regression Planning Networkscited by 32
  11. 2020Understanding the Power and Limitations of Teaching with Imperfect Knowledgecited by 23
  12. 2018Object-Oriented Dynamics Predictorcited by 15
  13. 2018Learning sparse relational transition modelscited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 1; 2026: 3.

7 papers.

  1. 2024BUMBLE: Unifying Reasoning and Acting with Vision-Language Models for Building-wide Mobile Manipulationcited by 31
  2. 2024Composing Pre-Trained Object-Centric Representations for Robotics From "What" and "Where" Foundation Modelscited by 16
  3. 2024Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstractioncited by 2
  4. 2025Sample-Efficient Behavior Cloning Using General Domain Knowledgecited by 2
  5. 2026InterPReT: Interactive Policy Restructuring and Training Enable Effective Imitation Learning from Laypersonscited by 2
  6. 2026Neurosymbolic Reasoning with Incremental Knowledge for Sample Efficient Hierarchical Reinforcement Learningcited by 0
  7. 2026Learning Action Models with Conditional and Quantified Effects via Uncertainty-Guided Explorationcited by 0