novastar111/pacman_v0
收藏资源简介:
该数据集包含用于自定义VisGym Pacman2D环境的行为克隆轨迹。每条记录代表一个成功的oracle episode,包含`image_prev`、`image`和`image_next`等历史条目,图像为JPEG base64字符串,源自greyblue9/pacman-python的视觉资源。环境设置包括:网格大小限制在7x7至12x12之间,easy难度使用9x9,hard难度使用11x11;实体包括Pacman、稀疏食物、墙壁和一个确定性幽灵。幽灵通过BFS距离追逐Pacman,动作空间为四个方向。数据集分为easy和hard两个难度级别,每个级别有训练和测试集,初始状态通过`init_state_hash`确保不重叠。
This dataset contains behavior-cloning trajectories for the custom VisGym Pacman2D environment. Each row is one successful oracle episode. The history entries include `image_prev`, `image`, and `image_next`; images are JPEG base64 strings rendered from the greyblue9/pacman-python visual assets used by the environment. Environment summary: Grid size is constrained to 7x7 through 12x12; Easy uses the 9x9 setting; hard uses the 11x11 setting; Entities are Pacman, sparse food, walls, and exactly one deterministic ghost. The ghost chases Pacman by BFS distance with fixed tie-break order up, down, left, right. The movement action space is four directions. Splits include easy and hard difficulty levels, each with train and test sets, and initial states are checked to be disjoint by `init_state_hash`.




