People routinely infer the goals and intentions of others from both actions and words. How might we build assistive machines that do the same? This talk will first introduce Bayesian inverse planning as a general framework for goal inference. I will then show how these problems can be solved accurately and efficiently via sequential inverse plan/policy search (SIPS), a family of algorithms that model agents as online model-based planners, and use programmable particle filtering to rapidly infer agents' goals and plans from observations of their behavior. Through the use of both incremental algorithms and compiler optimizations for model-based planning, SIPS can be made to run in (faster than) real-time.
Because SIPS is implemented using probabilistic programming, it is highly configurable. For example, SIPS can be used to model boundedly-rational agents, allowing us to infer an agent's goals even when they make planning mistakes. SIPS can also handle language input: By using large language models (LLMs) as likelihood functions over how people communicate their plans in natural language, SIPS can infer human plans from incomplete or ambiguous instructions. Finally, SIPS can be integrated with conditional priors over human goals that are learned from data, allowing us to scale online goal inference to open-ended settings with hundreds of possible goals. These advances pave the way towards fast, flexible, and grounded inferences over the infinite variety of human goals, furthering the development of human-aligned assistive systems.
Bio:
Tan Zhi-Xuan is a 5th year PhD student in the Computational Cognitive Science and Probabilistic Computing Groups at MIT. Their research sits at the intersection of AI and cognitive science, asking questions like: How can we specify and perform inference over rich yet structured generative models of human decision-making, in order to accurately infer human goals, values, and norms? To answer these questions, Xuan's work includes the development of probabilistic programming and model-based planning infrastructure, so as to enable fast and flexible Bayesian inference over complex models of agents and their environments.