mlsanityData to 14 Oct 2026

Quantifying Generalisation in Imitation Learning

arXiv 2509.24784 ↗First posted 29 Sep 2025cs.LG cs.AIcited by 0

On the map: Offline RL and imitation learning from data → Imitation learning methods

Abstract (arXiv)

Imitation learning benchmarks often lack sufficient variation between training and evaluation, limiting meaningful generalisation assessment. We introduce Labyrinth, a benchmarking environment designed to test generalisation with precise control over structure, start and goal positions, and task complexity. It enables verifiably distinct training, evaluation, and test settings. Labyrinth provides a discrete, fully observable state space and known optimal actions, supporting interpretability and fine-grained evaluation. Its flexible setup allows targeted testing of generalisation factors and includes variants like partial observability, key-and-door tasks, and ice-floor hazards. By enabling controlled, reproducible experiments, Labyrinth advances the evaluation of generalisation in imitation learning and provides a valuable tool for developing more robust agents.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data. Builds on 18 of its 29 references that are in the map. First posted on arXiv 29 Sep 2025.

Builds on

18 of 29 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024Explorative Imitation Learning: A Path Signature Approach for Continuous Environments5 Jul
  2. 2024Imitation Learning Datasets: A Toolkit For Creating Datasets, Training Agents and Benchmarking1 Mar
  3. 2023MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from Observations30 Mar
  4. 2021Off-Policy Imitation Learning from Observations25 Feb
  5. 2020Imitating Unknown Policies via Exploration13 Aug
  6. 2018Behavioral Cloning from Observation4 May

Other references · 12

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  3. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  4. 2016Generative Adversarial Imitation Learningcited by 1,597
  5. 2018DeepMind Control Suitecited by 956
  6. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 483
  7. 2023Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Taskscited by 327
  8. 2021Benchmarking the Spectrum of Agent Capabilitiescited by 200
  9. 2018Playing hard exploration games by watching YouTubecited by 99
  10. 2025Meta-World+: An Improved, Standardized, RL Benchmarkcited by 43
  11. 2023Is Imitation All You Need? Generalized Decision-Making with Dual-Phase Trainingcited by 18
  12. 2024DiffTORI: Differentiable Trajectory Optimization for Deep Reinforcement and Imitation Learningcited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Generalization Capability for Imitation Learning
  2. 2023Decomposing the Generalization Gap in Imitation Learning for Visual Robotic Manipulation
  3. 2020The MAGICAL Benchmark for Robust Imitation
  4. 2020Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations
  5. 2025Imitation Learning in the Deep Learning Era: A Novel Taxonomy and Recent Advances
  6. 2026Beyond Mimicry: Toward Lifelong Adaptability in Imitation Learning
  7. 2021Imitation Learning: Progress, Taxonomies and Challenges
  8. 2024Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations