Team

My current fundamental and applied research interests are in reinforcement learning, human-in-the-loop AI, multi-agent systems, and robotics.

My research interests lie in the area of reinforcement learning, especially in the fields of exploration, representation learning, transfer learning, policy search, and multi-objective optimization. Recently, I have been working on methods that move away from the classic tabula-rasa paradigm towards a more practical transfer framework. More specifically, I am interested in (1) better understanding state representation learning from rich and diverse inputs, (2) developing task-agnostic exploration policies, and (3) developing policy architectures for transfer/continual learning of state representations and exploration policies.

My major research interests include deep reinforcement learning (DRL) and multiagent systems, especially in how to achieve efficient, generalized, and scalable RL and multiagent RL through transfer/multi-task learning, hierarchical learning, and opponent modeling. I am also interested in efficient exploration in RL and multiagent RL. Currently, I am working on 1) how to effectively transfer knowledge in cross-domain settings; 2) how to improve RL generalization via symbolic planning.

My current research focus is on how to make RL agents learn effectively using knowledge leveraged from humans or other agents. I am interested in various kinds of advice modalities from humans with varying degrees of expertise and want to build systems that can seamlessly integrate such knowledge into a decision making framework. I am also interested in data efficient learning paradigms like active learning and cost-sensitive learning.

I am interested in studying the influence of human-agent-environment interaction and how this interaction can benefit both humans and AI agents. I question how to optimize agents' intervention or environment modification to help people thrive in different settings: academically (as an intelligent tutor) or in others like healthcare, where the agent's timely involvement may facilitate rehabilitation.

Research Interests: RL, Robotics, Human in loop learning, imitation learning

Research interests: My goal is to build AI agents not necessarily indistinguishable but compatible with humans and other intelligent agencies in a wide range of dynamic environments. To this end, I work at the intersection of deep reinforcement learning and human-AI interaction.

Daniel May, co-founder of a startup (TREX-Ai) focused on deep reinforcement learning for decentralized, automated multi-building energy management, researches bridging the gap between simulation and real-world applications for reinforcement learning agents under partial observability, and mixed multi-agent systems training under partial observability. In addition, he enjoys reading mathematical studies on the convergence behavior, loss landscapes, and capabilities of modern machine learning models.

Laura's research interests include reinforcement learning, human-robot interaction, biomechatronics, and assistive robotics. Drawing inspiration from her anatomical studies, Laura’s research aims to develop control methods for robotic manipulation with the goal of increased functionality, usability, reliability, and safety in the real-world.

I believe that I am in a continuous and life long process of learning which drives my passion for trying out new technologies and learning new skills. My interest areas include Reinforcement Learning, Deep Learning, Machine Learning, and Natural Language Processing.

Interested in the intersection between AI and psychology and how to apply human learning methods to AI agents. My research interests includes reinforcement learning and deep learning.

My research interests are an intersection between human and AI, how human can help agents to improve, or agents can help human to learn. I am interested in Reinforcement Learning, Natural Language Processing and Deep learning.

I apply RL to the home battery charging problem, and I investigate the use of ensembles in improving generalization in RL.

Currently working on analyzing the different modalities of human assisted reinforcement learning

Currently working on the SoundHunters to personalize learning of Cree Sounds with User Modelling and Machine Learning.

Currently working as the front end developer for HIPPO Gym

Currently working on the Human-AI interaction system for latent fingerprint

Currently working on implementing Hammer algorithm in SMARTS multi agent scenario.

Thesis: A framework for Safe Evaluation of Offline Learning, Fall 2021

Thesis: The Impact of Different Summaries as Reinforcement Learning Explanations on Human Performance And Perception, Summer 2021

Thesis: Transfer in Deep Reinforcement Learning: How an Agent Can Leverage Knowledge From Another Agent, A Human, or Itself, Spring 2021

Thesis: Knowledge Transfer in Reinforcement Learning: How Agents Should Benefit from Prior Knowledge, Fall 2019

Thesis: Teaching Effectiveness of Intelligent Tutoring Systems, Spring 2019

Thesis: Learning from Human Teachers — Supporting How People Want to Teach in Interactive Machine Learning, Summer 2018

Thesis: TINGLE — Topic-Independent Gamification Learning Environment, Summer 2018

Thesis: Policy Advice, Non-convex and Distributed Optimization in Reinforcement Learning, Fall 2016

Thesis: Regret Minimization with Function Approximation in Extensive-Form Games, Summer 2020

Thesis: Useful Policy Invariant Shaping from Arbitrary Advice, Winter 2020

Thesis: Accelerate the Learning Speed of Deep Reinforcement Learning by Pre- training with Non-Expert Human Demonstrations, Spring 2019

Thesis: Engineering a Smart Scarecrow: Bird Deterrence with Drones, Spring 2017

Thesis: Development of the Baton: A Novel Precision Delivery Drone, Summer 2017

Thesis: Modifying Smart Home to Smart Phone Notifications using Reinforcement Learning Algorithms, Spring 2017