WordCraft：一个对常识代理进行基准测试的环境
WordCraft: An Environment for Benchmarking Commonsense Agents
摘要：
快速解决各种现实任务的能力需要对世界有常识性的理解。然而，如何最好地从自然语言语料库中提取这些知识，并将其与强化学习（RL）代理集成仍然是一个开放的挑战。这在一定程度上是由于缺乏轻量级的仿真环境，充分反映了现实世界的语义，并提供知识源接地相对于RL环境中的观察。为了更好地研究利用常识知识的代理，我们提出了WordCraft，一个基于Little Alchemy 2的RL环境。这个轻量级的环境运行速度很快，并建立在受现实世界语义启发的实体和关系之上。我们在这个新的基准上评估了几种表示学习方法，并提出了一种将知识图谱与RL代理集成的新方法。
英文摘要：
The ability to quickly solve a wide range of real-world tasks requires a commonsense understanding of the world. Yet, how to best extract such knowledge from natural language corpora and integrate it with reinforcement learning (RL) agents remains an open challenge. This is partly due to the lack of lightweight simulation environments that sufficiently reflect the semantics of the real world and provide knowledge sources grounded with respect to observations in an RL environment. To better enable research on agents making use of commonsense knowledge, we propose WordCraft, an RL environment based on Little Alchemy 2. This lightweight environment is fast to run and built upon entities and relations inspired by real-world semantics. We evaluate several representation learning methods on this new benchmark and propose a new method for integrating knowledge graphs with an RL agent.
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。
