mlsanityData to 7 Oct 2026

Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search

arXiv 2206.00702 ↗First posted 1 Jun 2022cs.AI cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

Complex reasoning problems contain states that vary in the computational cost required to determine a good action plan. Taking advantage of this property, we propose Adaptive Subgoal Search (AdaSubS), a search method that adaptively adjusts the planning horizon. To this end, AdaSubS generates diverse sets of subgoals at different distances. A verification mechanism is employed to filter out unreachable subgoals swiftly, allowing to focus on feasible further subgoals. In this way, AdaSubS benefits from the efficiency of planning with longer subgoals and the fine control with the shorter ones, and thus scales well to difficult planning problems. We show that AdaSubS significantly surpasses hierarchical planning algorithms on three complex reasoning tasks: Sokoban, the Rubik's Cube, and inequality proving benchmark INT.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 33 of its 57 references that are in the map. First posted on arXiv 1 Jun 2022.

Builds on

33 of 57 references.

References · 33

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  3. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  4. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
  5. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,168
  6. 2017Hindsight Experience Replaycited by 1,096
  7. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,028
  8. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 723
  9. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 490
  10. 2020Generative Language Modeling for Automated Theorem Provingcited by 379
  11. 2016Learning to reinforcement learncited by 369
  12. 2018Semi-parametric Topological Memory for Navigationcited by 203
21 more
  1. 2020What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Studycited by 157
  2. 2018Multi-task Deep Reinforcement Learning with PopArtcited by 138
  3. 2014The LAMA Planner: Guiding Cost-Based Anytime Planning with Landmarkscited by 86
  4. 2019Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generationcited by 83
  5. 2020World Model as a Graph: Learning Latent Landmarks for Planningcited by 67
  6. 2019An investigation of model-free planningcited by 64
  7. 2020Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictorscited by 60
  8. 2018Learning Plannable Representations with Causal InfoGANcited by 56
  9. 2020INT: An Inequality Benchmark for Evaluating Generalization in Theorem Provingcited by 44
  10. 2018Time-Agnostic Prediction: Predicting Predictable Video Framescited by 37
  11. 2019Variational Temporal Abstractioncited by 37
  12. 2020Sub-Goal Trees -- a Framework for Goal-Based Reinforcement Learningcited by 27
  13. 2022MuZero with Self-competition for Rate Control in VP9 Video Compressioncited by 27
  14. 2020Hallucinative Topological Memory for Zero-Shot Visual Planningcited by 25
  15. 2019Dynamics Learning with Cascaded Variational Inference for Multi-Step Manipulationcited by 22
  16. 2021Subgoal Search For Complex Reasoning Taskscited by 21
  17. 2019Keyframing the Future: Keyframe Discovery for Visual Prediction and Planningcited by 20
  18. 2017Intention-Net: Integrating Planning and Deep Learning for Goal-Directed Autonomous Navigationcited by 19
  19. 2020Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planningcited by 19
  20. 2020Efficient Black-Box Planning Using Macro-Actions with Focused Effectscited by 9
  21. 2019Uncertainty-sensitive Learning and Planning with Ensemblescited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 3; 2025: 4; 2026: 1.

12 papers.

  1. 2023Thought Cloning: Learning to Think while Acting by Imitating Human Thinkingcited by 30
  2. 2024Double-Ended Synthesis Planning with Goal-Constrained Bidirectional Searchcited by 24
  3. 2025PDE-Controller: LLMs for Autoformalization and Reasoning of PDEscited by 23
  4. 2023Hierarchical Imitation Learning with Vector Quantized Modelscited by 15
  5. 2025Flattening Hierarchies with Policy Bootstrappingcited by 8
  6. 2023Hybrid Search for Efficient Planning with Completeness Guaranteescited by 6
  7. 2023On the Theory of Risk-Aware Agents: Bridging Actor-Critic and Economicscited by 6
  8. 2025Contrastive Representations for Temporal Reasoningcited by 5
  9. 2024tsGT: Stochastic Time Series Modeling With Transformercited by 1
  10. 2024What Matters in Hierarchical Search for Combinatorial Reasoning Problems?cited by 1
  11. 2025Subgoal-Guided Policy Heuristic Search with Learned Subgoalscited by 1
  12. 2026Structure-Induced Information for Rerooting Levin Tree Searchcited by 0