Adaptive Locomotion of Soft Microrobots
Networked Control and Communication
Controller Learning using Bayesian Optimization
Event-based Wireless Control of Cyber-physical Systems
Model-based Reinforcement Learning for PID Control
Learning Probabilistic Dynamics Models
Gaussian Filtering as Variational Inference
Measuring the Cost of Planning with Bayesian Inverse Reinforcement Learning
In this project, we investigate to which extent seemingly irrational planning decisions are a consequence of how people individually experience the costs and benefits of deliberate decision-making. We start from the empirically-grounded assumption that many sub-optimal decisions arise from being short-sighted when balancing the costs and benefits of a particular decision. To achieve this, we leverage Bayesian Inverse Reinforcement Learning [Ramachandran and Amir, IJCAI 2007] to infer experienced reward functions. In future work, we will investigate personalized interventions based on differences in these experienced costs. This work may result in insights about human decision-making, applicable to a wide range of domains such as public policy, psychiatric treatment, and the field of education.
Video
Members
Publications