Reward design for reinforcement learning agents can be difficult in situations where one not only wants the agent to achieve some effect in the world but where one also cares about how that effect is achieved. For example, we might wish for an agent to adhere to a tacit understanding of commonsense, align itself to a preference for how to behave for purposes of safety, or taking on a particular role in an interactive game. Storytelling is a mode for communicating tacit procedural knowledge. We introduce a technique, Story Shaping, in which a reinforcement learning agent infers tacit knowledge from an exemplar story of how to accomplish a task and intrinsically rewards itself for performing actions that make its current environment adhere to that of the inferred story world. Specifically, Story Shaping infers a knowledge graph representation of the world state from observations, and also infers a knowledge graph from the exemplar story. An intrinsic reward is generated based on the similarity between the agent's inferred world state graph and the inferred story world graph. We conducted experiments in text-based games requiring commonsense reasoning and shaping the behaviors of agents as virtual game characters.
对强化学习代理的奖励设计可能会在不仅希望代理在世界中实现某种效果,而且还关心如何实现这种效果的情况下变得困难。例如,我们 might wish for an agent to adhere to a tacit understanding of commonsense, align itself to a preference for how to behave for safety, or take on a particular role in an interactive game. 故事讲述是一种传达隐含程序知识的方式。我们介绍了一种技术,称为故事重构,该技术使得强化学习代理可以从一个完成任务的典型故事推断隐含知识,并自我奖励进行使其当前环境与推断故事世界相似的行动。具体来说,故事重构从观察中推断世界状态的知识图表示,并从典型故事推断知识图。一种自我奖励机制基于代理的推断世界状态图与推断故事世界图之间的相似性。我们在文本游戏中要求常识推理,并将代理的行为塑造成虚拟游戏角色的行为。我们进行了实验,在需要常识推理的文本游戏中调整代理的行为。