连续离线强化学习导航任务基准测试
A Continual Offline Reinforcement Learning Benchmark for Navigation Tasks
AI总结：
本文提出一个连续离线强化学习导航任务基准测试，通过视频游戏场景评估算法性能，解决灾难性遗忘、任务适应和内存效率等关键挑战。
摘要：
自主代理在机器人或视频游戏模拟等领域中必须适应变化的任务而不遗忘之前的任务。这个过程称为连续强化学习，提出了非平凡的挑战，从防止灾难性遗忘到确保所考虑方法的可扩展性。基于最近的进展，我们引入了一个基准，提供了一系列视频游戏导航场景，从而填补了文献中的空白，并捕捉到关键挑战：灾难性遗忘、任务适应和内存效率。我们定义了一组各种任务和数据集、评估协议和指标，以评估算法的性能，包括最先进的基线。我们的基准不仅旨在促进可重复的研究，加速游戏连续强化学习的进步，还提供了一个可重复的框架用于生产流程——帮助从业者识别并应用有效的做法。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
