Aerospace Controls Laboratory

Shayegan Omidshafiei


shayegan [at] mit [dot] edu


Sharing in Multiagent Reinforcement Learning
Samir Wadhwania, Dong-Ki Kim, Shayegan Omidshafiei, 2019

Sharing information during learning in multiagent environments can reduce the need for each agent to explore the entire state space, leading to reduced learning time.

Learning to Teach in Cooperative MARL
Dong-Ki Kim, Shayegan Omidshafiei, 2018

Our algorithm, Learning to Coordinate and Teach Reinforcement (LeCTR), addresses peer-to-peer teaching in cooperative multiagent reinforcement learning.

Crossmodal Attentive Skill Learner
Shayegan Omidshafiei, Dong-Ki Kim, 2018

This work introduces the crossmodal learning paradigm and addresses the problem of learning in a high-dimensional domain with multiple sensory inputs.

Decentralized Multi-task Learning
Shayegan Omidshafiei, 2018

This work formalizes and addresses the problem of multi-task multiagent reinforcement learning under partial observability.

Decentralized Control of Multi-Robot Partially Observable Markov Decision Processes using Belief Space Macro-actions
Shayegan Omidshafiei, Ali-akbar Ahga-mohammadi, Christopher Amato, Shih-Yuan Liu, Miao Liu, 2014

This work extends the Dec-POMDP model to the Decentralized Partially Observable Semi-Markov Decision Process (Dec-POSMDP) to take advantage of high-level representations that are natural for multi-robot problems and to facilitate scalable solutions to large discrete and continuous problems.

Measurable Augmented Reality for Prototyping Cyber-Physical Systems (MAR-CPS)
Shayegan Omidshafiei, Ali-akbar Ahga-mohammadi, Steven Chen, N. Kemal Ure, 2014

We propose a platform designed to transform indoor laboratories into controlled simulations of outdoor environments.