XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning

2024-06-13 · Alexander Nikulin, Ilya Zisman, Alexey Zemtsov, Viacheslav Sinii, Vladislav Kurenkov, Sergey Kolesnikov

Following the success of the in-context learning paradigm in large-scale language and computer vision models, the recently emerging field of in-context reinforcement learning is experiencing a rapid growth. However, its development has been held back by the lack of challenging benchmarks, as all the experiments have been carried out in simple environments and on small-scale datasets. We present \textbf{XLand-100B}, a large-scale dataset for in-context reinforcement learning based on the XLand-MiniGrid environment, as a first step to alleviate this problem. It contains complete learning histories for nearly $30,000$ different tasks, covering $100$B transitions and $2.5$B episodes. It took $50,000$ GPU hours to collect the dataset, which is beyond the reach of most academic labs. Along with the dataset, we provide the utilities to reproduce or expand it even further. With this substantial effort, we aim to democratize research in the rapidly growing field of in-context reinforcement learning and provide a solid foundation for further scaling. The code is open-source and available under Apache 2.0 licence at https://github.com/dunno-lab/xland-minigrid-datasets.

📄 PDF Abstract BibTeX arXiv:2406.08973

Code (0)

등록된 구현이 없습니다.

Tasks

GPUIn-Context LearningIn-Context Reinforcement Learningreinforcement-learning Reinforcement Learning

XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX

2023-12-19 · Alexander Nikulin, Vladislav Kurenkov, Ilya Zisman, Artem Agarkov 외

Inspired by the diversity and depth of XLand and the simplicity and minimalism of MiniGrid, we present XLand-MiniGrid, a suite of tools and grid-world environments for meta-reinforcement learning research. Written in JAX…

Diversity GPU Meta-Learning Meta Reinforcement Learning+2

Yes, Q-learning Helps Offline In-Context RL

2025-02-24 · Denis Tarasov, Alexander Nikulin, Ilya Zisman, Albina Klepach 외

Existing offline in-context reinforcement learning (ICRL) methods have predominantly relied on supervised training objectives, which are known to have limitations in offline RL settings. In this study, we explore the int…

In-Context Reinforcement Learning MuJoCo Offline RL Q-Learning+1

Decomposing and Steering Functional Metacognition in Large Language Models

2026-05-09 · Yanshi Li, Xueru Bai, Shuman Liu, Haibo Zhang 외 arxiv

Large language models (LLMs) increasingly exhibit behaviors suggesting awareness of their evaluation context, often adapting their reasoning strategies in benchmark settings. Prior work has shown that such evaluation awa…

NiceWebRL: a Python library for human subject experiments with reinforcement learning environments

2025-08-21 · Wilka Carvalho, Vikram Goddla, Ishaan Sinha, Hoon Shin 외 arxiv

We present NiceWebRL, a research tool that enables researchers to use machine reinforcement learning (RL) environments for online human subject experiments. NiceWebRL is a Python library that allows any Jax-based environ…

Reinforcement Learning

CODE-SHARP: Continuous Open-ended Discovery and Evolution of Skills as Hierarchical Reward Programs

2026-02-10 · Richard Bornemann, Pierluigi Vito Amadori, Antoine Cully arxiv

A core quality of general intelligence is the ability to open-endedly expand and evolve its set of mastered skills autonomously. While recent Foundation Model (FM) driven approaches have shown promising results towards t…