通过社会互动和好奇心驱动的多目标学习建立语言基础
Language Grounding through Social Interactions and Curiosity-Driven Multi-Goal Learning
摘要：
自主强化学习代理，如儿童，没有访问预定义的目标和奖励功能。他们必须发现潜在的目标，学习自己的奖励功能，并参与自己的学习轨迹。然而，儿童从接触语言中受益，帮助组织和调解他们的思想。我们提出了LE2（语言增强的探索），一个学习算法利用内在的动机和自然语言（NL）与描述性的社会伙伴（SP）的互动。使用来自SP的NL描述，它可以学习NL条件奖励函数来制定内在动机目标探索的目标，并学习目标条件策略。通过探索，从SP收集描述，并共同学习奖励函数和策略，代理将NL描述转化为真实的行为目标。从早期发现的简单目标到通过对简单目标进行实验发现的更复杂目标，我们的智能体自主构建自己的行为库。这种自然发生的课程是由代理人的内在动机产生的主动学习课程补充的。实验提出了一个模拟的机器人手臂，与几个对象，包括工具。
英文摘要：
Autonomous reinforcement learning agents, like children, do not have access to predefined goals and reward functions. They must discover potential goals, learn their own reward functions and engage in their own learning trajectory. Children, however, benefit from exposure to language, helping to organize and mediate their thought. We propose LE2 (Language Enhanced Exploration), a learning algorithm leveraging intrinsic motivations and natural language (NL) interactions with a descriptive social partner (SP). Using NL descriptions from the SP, it can learn an NL-conditioned reward function to formulate goals for intrinsically motivated goal exploration and learn a goal-conditioned policy. By exploring, collecting descriptions from the SP and jointly learning the reward function and the policy, the agent grounds NL descriptions into real behavioral goals. From simple goals discovered early to more complex goals discovered by experimenting on simpler ones, our agent autonomously builds its own behavioral repertoire. This naturally occurring curriculum is supplemented by an active learning curriculum resulting from the agent's intrinsic motivations. Experiments are presented with a simulated robotic arm that interacts with several objects including tools.
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。
