rl.0.1 game set

该数据集包含了多个级别的烹饪游戏，旨在在基于文本的游戏环境中训练和评估强化学习智能体。数据集被划分为训练集、验证集和测试集，并设有独立的、未见过的新关卡以评估智能体的泛化能力。规模上，共有8个级别，每个训练级别包含100个游戏，而验证和测试级别则各有20个游戏。该任务针对的是文本游戏中的强化学习。

This dataset comprises multiple levels of cooking-themed text-based games, intended for training and evaluating reinforcement learning agents in text-based game environments. The dataset is divided into training, validation, and test subsets, with independent and unseen new levels designed to assess the agents' generalization ability. In terms of scale, there are 8 levels in total. Each training level contains 100 game instances, while each validation and test level includes 20 game instances respectively. This task targets reinforcement learning in text-based games.