Pragmatic Instruction Following and Goal Assistance via Cooperative Language-Guided Inverse Planning (Exp 1)
You will watch animated scenarios showing a human and robot cooperating in a grid-world treasure game. The human wants to collect exactly one colored gem, and may give the robot instructions. After watching each scenario, you will judge which gem the human wants and how the robot should best assist.
Instruction FollowingGoal InferenceAssistance Judgment
Study metadata
- Authors
- Tan Zhi-Xuan, Lance Ying, Vikash Mansinghka, Joshua B. Tenenbaum
- Source
- Tan, Z.-X., Ying, L., Mansinghka, V., & Tenenbaum, J. B. (2024). Pragmatic instruction following and goal assistance via cooperative language-guided inverse planning. Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2024), 2094–2103. International Foundation for Autonomous Agents and Multiagent Systems.
- Slug
- zhi-xuan2024pragmatic-exp1