# Quantifying Generalisation in Imitation Learning

arXiv: https://arxiv.org/abs/2509.24784 · HTML: https://mlsanity.com/paper/2509.24784/

## 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.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [DeepMind Control Suite](https://mlsanity.com/paper/1801.00690/) (2018)
- [Behavioral Cloning from Observation](https://mlsanity.com/paper/1805.01954/) (2018)
- [Leveraging Procedural Generation to Benchmark Reinforcement Learning](https://mlsanity.com/paper/1912.01588/) (2019)
- [Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks](https://mlsanity.com/paper/2306.13831/) (2023)
- [Benchmarking the Spectrum of Agent Capabilities](https://mlsanity.com/paper/2109.06780/) (2021)
- [Playing hard exploration games by watching YouTube](https://mlsanity.com/paper/1805.11592/) (2018)
- [Off-Policy Imitation Learning from Observations](https://mlsanity.com/paper/2102.13185/) (2021)
- [Meta-World+: An Improved, Standardized, RL Benchmark](https://mlsanity.com/paper/2505.11289/) (2025)
- [MAHALO: Unifying Offline Reinforcement Learning and Imitation Learning from Observations](https://mlsanity.com/paper/2303.17156/) (2023)
- [Is Imitation All You Need? Generalized Decision-Making with Dual-Phase Training](https://mlsanity.com/paper/2307.07909/) (2023)
- [Imitating Unknown Policies via Exploration](https://mlsanity.com/paper/2008.05660/) (2020)
- [DiffTORI: Differentiable Trajectory Optimization for Deep Reinforcement and Imitation Learning](https://mlsanity.com/paper/2402.05421/) (2024)
- [Imitation Learning Datasets: A Toolkit For Creating Datasets, Training Agents and Benchmarking](https://mlsanity.com/paper/2403.00550/) (2024)
- [Explorative Imitation Learning: A Path Signature Approach for Continuous Environments](https://mlsanity.com/paper/2407.04856/) (2024)

## 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.