Avalon Dataset

Avalon is a benchmark for generalization in Reinforcement Learning (RL). The benchmark consists of a set of tasks in which embodied agents in highly diverse procedural 3D worlds must survive by navigating terrain, hunting or gathering food, and avoiding hazards. Avalon is unique among existing RL benchmarks in that the reward function, world dynamics, and action space are the same for every task, with tasks differentiated solely by altering the environment; its 20 tasks, ranging in complexity from eat and throw to hunt and navigate, each create worlds in which the agent must perform specific skills in order to survive. This benchmark setup enables investigations of generalization within tasks, between tasks, and to compositional tasks that require combining skills learned from previous tasks.

Avalon是一套针对强化学习（RL）泛化能力的基准测试。该基准测试由一系列任务组成，在这些任务中，身处高度多样化的程序化3D世界中的具身智能体必须通过在地形中导航、狩猎或采集食物以及规避危险来生存。Avalon在现有的RL基准测试中独具特色，因为在每一个任务中，其奖励函数、世界动态和动作空间均保持一致，而任务的差异化仅在于环境的改变；其20个任务，从进食与投掷到狩猎与导航，涵盖了从简单到复杂的多种复杂度，每个任务都构建了一个世界，其中的智能体必须展现出特定的技能才能存活。这种基准测试的设置，使得对任务内、任务间以及需要结合先前任务中学习到的技能的复合任务的泛化能力的研究成为可能。