Adverse experiences in childhood, ranging from neglect to resource scarcity to abuse, alter developmental trajectories and increase risk for reward-related psychopathologies. In humans, exposure to …
With few exceptions, robots today are unable to quickly acquire new manipulation skills in the real world. The modern data-driven approach to skill learning is …
Generally intelligent agents must learn and plan in complex environments, with sensors and actuators that support various behaviors and tasks. This complexity hinders decision making, …
How do humans learn to adaptively function in a fundamentally uncertain social world? Since we cannot directly observe the contents of other people’s minds, the …
Future collaborative robots must be capable of finding objects. As such a fundamental skill, we expect object search to eventually become an off-the-shelf capability for …
Reinforcement learning (RL) techniques have led to remarkable results in challenging domains such as Atari games, Go, and Starcraft, suggesting that practical applications lie just …
How synaptic plasticity in-vivo manages diverse properties of biological neural networks remains poorly understood. My collaborators and I address this by examining basic models of …
Background: Best subset selection for sparse linear regression is a classical statistical problem that has received renewed attention following a new approach to directly solve …
In both supervised and reinforcement settings, there exist learning problems that are hard due to having high computational or sample complexity. Researchers have shown, using …
Reinforcement learning (RL) is the study of the interaction between an environment and an artificial agent that learns to maximize reward through trial-and-error. Owing to …
In this work, I present an implemented model that can learn interactively from natural language, enabling non-expert human trainers to convey complex tasks to machines …
Reusing knowledge allows intelligent systems to learn solutions to complex tasks more quicker by avoiding re-learning the components of the solution from scratch. Recent advances …
Reinforcement learning defines the problem facing agents that learn to make good decisions through action and observation alone. To be effective problem solvers, such agents …
In this thesis, I explore the relevance of computational reinforcement learning to the philosophy of rationality and concept formation. I first argue that the framework …
Human teaching involves many forms of non-verbal behavior that unfold over the course of an interaction between a teacher and learner. Such processes facilitate the …
The basal ganglia has been implicated in motivational behavior, reinforcement learning, reward seeking, and action selection. The dual nature of these behaviors, i.e. encouragement vs. …
Declarative memory has long been known to depend on the medial temporal lobe memory system. Recently, there has been renewed focus on the relationship between …
A wealth of research shows how the dopaminergic frontostriatal system incrementally learns from<br/> rewards and punishments. Midbrain dopamine cells show phasic firing rate changes in …