构建游戏导航任务的持续强化学习基准，解决遗忘与适应难题。
A Continual Offline Reinforcement Learning Benchmark for Navigation Tasks
- 设计多场景游戏导航任务与数据集，模拟持续学习挑战。
- 提供评估协议与指标，涵盖遗忘率、适应速度和内存效率。
- 支持科研与工业落地，便于算法对比与实际应用。
在机器人或视频游戏模拟等领域的自主代理需在不遗忘旧任务的前提下适应新任务，这称为持续强化学习，面临灾难性遗忘与方法可扩展性等挑战。基于最新进展，我们引入一个基准，包含一系列视频游戏导航场景，填补了文献空白并捕捉关键挑战：灾难性遗忘、任务适应与内存效率。我们定义了多种任务、数据集、评估协议与性能指标，用于评估包括前沿基线在内的算法表现。该基准不仅促进可复现研究、加速游戏领域持续强化学习进展，还为生产流程提供可复现框架，帮助从业者识别并应用有效方法。
原文摘要 · Abstract (English)
Autonomous agents operating in domains such as robotics or video game simulations must adapt to changing tasks without forgetting about the previous ones. This process called Continual Reinforcement Learning poses non-trivial difficulties, from preventing catastrophic forgetting to ensuring the scalability of the approaches considered. Building on recent advances, we introduce a benchmark providing a suite of video-game navigation scenarios, thus filling a gap in the literature and capturing key challenges : catastrophic forgetting, task adaptation, and memory efficiency. We define a set of various tasks and datasets, evaluation protocols, and metrics to assess the performance of algorithms, including state-of-the-art baselines. Our benchmark is designed not only to foster reproducible research and to accelerate progress in continual reinforcement learning for gaming, but also to provide a reproducible framework for production pipelines -- helping practitioners to identify and to apply effective approaches.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。