图灵讲堂第24期
报告时间：2023年3月23日 16：30
报告地点：紫金港校区蒙民伟楼138报告厅
报告题目：Building Assistive Agents for Humans
报告人：吴翼（清华大学）
Abstract:
An long-term mission in AI is to develop general-purpose assistant or robot that can help humans solve arbitrary daily tasks. A perspective is that reinforcement learning would be the most foundamental technique towards this long-term mission. In this overview talk, Prof. Wu will give a high-level introduction of his team's efforts along this roadmap and how they develop assistive agents for interacting with humans.
Bio:
Yi Wu is now an assistant professor at institute for interdisciplinary information sciences (IIIS), Tsinghua university. He obtained his PhD degree from UC Berkeley in 2019 under the supervision of Prof. Stuart Russell and was a researcher at OpenAI before moving back to Tsinghua. His research focuses on improving the generalization capabilities of learning agents. He is broadly interested in a variety of topics in AI, including deep reinforcement learning, multi-agent systems, language grounding and robot learning. His representative works include value iteration network, the MADDPG/MAPPO algorithm and OpenAI's hide-and-seek project. He also received the best paper award at NIPS 2016.