I am interested in helping people improve their decisions, using techniques from reinforcement learning such as inverse reinforcement learning and shaping.
Prior to joining the lab, I worked as a research specialist in Yael Niv's lab at Princeton University. Before that, I worked as a research intern in Yossi Yovel's lab at Tel Aviv University and as an undergraduate research assistant in the Gabrieli Lab at MIT.
Which information is worth considering depends on how much effort it would take to acquire and process it. From this perspective people’s tendency to neglect considering the long-term consequences of their actions (present bias) might reflect that looking further into the future becomes increasingly more effortful. In this work, we introduce and validate the use of Bayesian Inverse Reinforcement Learning (BIRL) for measuring individual differences in the subjective costs of planning. We extend the resource-rational model of human planning introduced by Callaway, Lieder, et al. (2018) by parameterizing the cost of planning. Using BIRL, we show that increased subjective cost for considering future outcomes may be associated with both the present bias and acting without planning. Our results highlight testing the causal effects of the cost of planning on both present bias and mental effort avoidance as a promising direction for future work.
Our goal is to understand the principles of Perception, Action and Learning in autonomous systems that successfully interact with complex environments and to use this understanding to design future systems