A Song of Ice and Fire: Analyzing Textual Autotelic Agents in ScienceWorld

arxiv(2023)

引用 0|浏览37
暂无评分
摘要
Building open-ended agents that can autonomously discover a diversity of behaviours is one of the long-standing goals of artificial intelligence. This challenge can be studied in the framework of autotelic RL agents, i.e. agents that learn by selecting and pursuing their own goals, self-organizing a learning curriculum. Recent work identified language as a key dimension of autotelic learning, in particular because it enables abstract goal sampling and guidance from social peers for hindsight relabelling. Within this perspective, we study the following open scientific questions: What is the impact of hindsight feedback from a social peer (e.g. selective vs. exhaustive)? How can the agent learn from very rare language goal examples in its experience replay? How can multiple forms of exploration be combined, and take advantage of easier goals as stepping stones to reach harder ones? To address these questions, we use ScienceWorld, a textual environment with rich abstract and combinatorial physics. We show the importance of selectivity from the social peer's feedback; that experience replay needs to over-sample examples of rare goals; and that following self-generated goal sequences where the agent's competence is intermediate leads to significant improvements in final performance.
更多
查看译文
关键词
textual autotelic agents
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要