An Investigation into the Open World Survival Game Crafter

Aleksandar Stanić, Yujin Tang, David Ha, Jürgen Schmidhuber

Keywords: Crafter benchmark, baselines, OOD generalizaiton, attention-based agents

TL;DR: We show that simple baselines outperform all previous agents on Crafter, introduce new OOD generalization environments and study attention-based agents on them.

Abstract: We share our experience with the recently released Crafter benchmark, a 2D open world survival game. Crafter allows tractable investigation of novel agents and their generalization, exploration and long-term reasoning capabilities. We evaluate agents on the original Crafter environment, as well as on a newly introduced set of generalization environments, suitable for evaluating agents' robustness to unseen objects and fast-adaptation (meta-learning) capabilities. Through several experiments we provide a couple of critical insights that are of general interest for future work on Crafter. We find that: (1) Simple agents with tuned hyper-parameters outperform all previous agents. (2) Feedforward agents can unlock almost all achievements by relying on the inventory display. (3) Recurrent agents improve on feedforward ones, also without the inventory information. (4) Baseline agents fail to generalize to OOD objects, object-centric agents improve over them. We will open-source our code.