Online Bayesian Goal Inference for Boundedly-Rational Planning Agents (Exp 1)
You will watch short animations showing an agent navigating through a gridworld with doors, keys, and colored gems. The animations will be shown incrementally — you will see the agent's trajectory up to a certain point and then estimate how likely the agent is pursuing each of the three gems as its goal. As more of the trajectory is revealed, you will update your estimates.
Theory of MindGoal InferenceSocial Cognition
Study metadata
- Authors
- Tan Zhi-Xuan, Jordyn L. Mann, Tom Silver, Joshua B. Tenenbaum, Vikash K. Mansinghka
- Source
- Zhi-Xuan, T., Mann, J. L., Silver, T., Tenenbaum, J. B., & Mansinghka, V. K. (2020). Online Bayesian Goal Inference for Boundedly-Rational Planning Agents (Version 2). arXiv. https://doi.org/10.48550/ARXIV.2006.07532
- Slug
- zhi-xuan2020online-exp1