← Back to papers
2024 NIPS NeurIPS 2024

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

Abstract

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, XLand-MiniGrid is designed to be highly scalable and can potentially run on GPU or TPU accelerators, democratizing large-scale experimentation with limited resources. Along with the environments, XLand-MiniGrid provides pre-sampled benchmarks with millions of unique tasks of varying difficulty and easy-to-use baselines that allow users to quickly start training adaptive agents. In addition, we have conducted a preliminary analysis of scaling and generalization, showing that our baselines are capable of reaching millions of steps per second during training and validating that the proposed benchmarks are challenging. XLand-MiniGrid is open-source and available at \url{https://github.com/corl-team/xland-minigrid}.

🧭 Keyword Pioneer — reinforcement learning benchmark
🐝 Cross-Pollinator — Artificial Intelligence, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Speech & Audio
🌉 Interdisciplinary Bridge — Artificial Intelligence and Deep Learning and Machine Learning and Reinforcement Learning

Authors

Alexander Nikulin , Vladislav Kurenkov , Ilya Zisman , Artem Agarkov , Viacheslav Sinii , Sergey Kolesnikov

Topics

Artificial Intelligence > Core AI > Agent Systems Artificial Intelligence > Learning Paradigms > Meta-Learning Deep Learning > Architectures > Transformers Reinforcement Learning > Methods > Deep RL Reinforcement Learning > Methods > Policy Learning Reinforcement Learning > Applications > Robotics Machine Learning > Learning Paradigms > Meta-Learning Machine Learning > Learning Types > Meta-Learning Deep Learning > Learning Types > Reinforcement Learning Deep Learning > Learning Types > Meta-Learning Reinforcement Learning > Methods > Meta-Learning

Keywords

multi-task learning few-shot learning scalable training adaptive agent meta-reinforcement learning task distribution reinforcement learning benchmark scalable computing multi-task adaptation gradient-based meta-learning environment simulation environment benchmarking scalable environment
Download PDF

Related papers

SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers 2024
Training for Stable Explanation for Free 2024
NeuralSolver: Learning Algorithms For Consistent and Efficient Extrapolation Across General Tasks 2024
Expectation Alignment: Handling Reward Misspecification in the Presence of Expectation Mismatch 2024
MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence 2024