mlsanityData to 7 Oct 2026

Learning to Search Better Than Your Teacher

arXiv 1502.02206 ↗First posted 8 Feb 2015cs.LG stat.MLcited by 50

Not on the map. Why?

Cited by 22 in Offline RL and imitation learning from data, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Methods for learning to search for structured prediction typically imitate a reference policy, with existing theoretical guarantees demonstrating low regret compared to that reference. This is unsatisfactory in many applications where the reference policy is suboptimal and the goal of learning is to improve upon it. Can learning to search work even when the reference is poor? We provide a new learning to search algorithm, LOLS, which does well relative to the reference policy, but additionally guarantees low regret compared to deviations from the learned policy: a local-optimality guarantee. Consequently, LOLS can improve upon the reference policy, unlike previous algorithms. This enables us to develop structured contextual bandits, a partial information structured prediction setting with many potential applications.

Key facts. Cited by 50 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Feb 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2017: 1; 2018: 6; 2019: 3; 2020: 5; 2021: 5; 2022: 9; 2023: 6; 2024: 7; 2025: 3; 2026: 5.

50 papers.

Sort:

By area:

  1. 2018An Algorithmic Perspective on Imitation Learningcited by 455
  2. 2024Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoningcited by 267
  3. 2022Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimizationcited by 244
  4. 2024The pitfalls of next-token predictioncited by 156
  5. 2024From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Modelscited by 136
  6. 2019Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learningcited by 100
  7. 2019Provably Efficient Imitation Learning from Observation Alonecited by 78
  8. 2018Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Interventioncited by 77
  9. 2017Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedbackcited by 71
  10. 2020Autoregressive Knowledge Distillation through Imitation Learningcited by 68
  11. 2023Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorldcited by 65
  12. 2022Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progresscited by 63
38 more
  1. 2024Policy Decorator: Model-Agnostic Online Refinement for Large Policy Modelcited by 60
  2. 2021Imitation Learning: Progress, Taxonomies and Challengescited by 56
  3. 2023Learning to Generate Better Than Your LLMcited by 49
  4. 2022Autoregressive Structured Prediction with Language Modelscited by 43
  5. 2020Provable Representation Learning for Imitation Learning via Bi-level Optimizationcited by 41
  6. 2018Truncated Horizon Policy Search: Combining Reinforcement Learning & Imitation Learningcited by 39
  7. 2023Inverse Reinforcement Learning without Reinforcement Learningcited by 35
  8. 2023CCIL: Continuity-based Data Augmentation for Corrective Imitation Learningcited by 26
  9. 2022An Imitation Learning Curriculum for Text Editing with Non-Autoregressive Modelscited by 20
  10. 2022CrossBeam: Learning to Search in Bottom-Up Program Synthesiscited by 18
  11. 2025A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Searchcited by 16
  12. 2018OIL: Observational Imitation Learningcited by 11
  13. 2019An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generationcited by 11
  14. 2022Iterative Document-level Information Extraction via Imitation Learningcited by 11
  15. 2022Teacher Forcing Recovers Reward Functions for Text Generationcited by 11
  16. 2018Learning Beam Search Policies via Imitation Learningcited by 9
  17. 2021Branch and Bound in Mixed Integer Linear Programming Problems: A Survey of Techniques and Trendscited by 9
  18. 2022Learning Graph Search Heuristicscited by 7
  19. 2018Accelerating Imitation Learning with Predictive Modelscited by 6
  20. 2021Incremental Beam Manipulation for Natural Language Generationcited by 6
  21. 2023LambdaBeam: Neural Program Search with Higher-Order Functions and Lambdascited by 6
  22. 2022Learning to design without prior data: Discovering generalizable design strategies using deep learning and tree searchcited by 5
  23. 2020Active Imitation Learning from Multiple Non-Deterministic Teachers: Formulation, Challenges, and Algorithmscited by 4
  24. 2025Guided Policy Optimization under Partial Observabilitycited by 3
  25. 2025To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable Reinforcement Learningcited by 3
  26. 2026Stable Agentic Control: Tool-Mediated LLM Architecture for Autonomous Cyber Defensecited by 3
  27. 2021Computational Morphology with Neural Network Approachescited by 2
  28. 2026Speculative Rollback Correction for Quality-Diverse Web Agent Imitationcited by 2
  29. 2020Explaining Fast Improvement in Online Imitation Learningcited by 1
  30. 2020Hybrid Imitation Learning for Real-Time Service Restoration in Resilient Distribution Systemscited by 1
  31. 2021Improving Scheduled Sampling with Elastic Weight Consolidation for Neural Machine Translationcited by 1
  32. 2023Genetic Imitation Learning by Reward Extrapolationcited by 1
  33. 2024Oracle-Efficient Reinforcement Learning for Max Value Ensemblescited by 1
  34. 2026Multi-Agent Transactive Memorycited by 1
  35. 2024Beyond MLE: Investigating SEARNN for Low-Resourced Neural Machine Translationcited by 0
  36. 2024Improving Autoregressive Training with Dynamic Oraclescited by 0
  37. 2026Forward-Free Diffusion Language Models with BPTT-Free Looped Refinementcited by 0
  38. 2026Learning Source Acquisition Policies by Offline Planningcited by 0