The Autonomous Learning Laboratory (ALL) carries out foundational interdisciplinary research on machine learning and computational models of biological learning. Autonomous learning refers to what a self-reliant agent must do to learn from its own experiences.
The long-term goals of the laboratory are to develop more capable artificial agents, to improve our understanding of biological learning and its neural basis, and to forge stronger links between studies of learning by computer scientists, engineers, neuroscientists, and psychologists.
Areas of interest include reinforcement learning, machine learning, abstraction, hierarchy, motor control, robotics, computational neuroscience and developmental psychology.
Lab News
Sridhar Mahadevan's IJCAI 2016 Tutorial on A Unified Framework for Transfer Learning
New grant to investigate Mars with deep learning highlighted in the news!
Kristina Fedorenko won the Oustanding Teaching Assistant Award @ UMass' OAA '16!
Sridhar Mahadevan & Andy Barto
are
interviewed about AlphaGo's big win!
Congratulations to our recent student award winners:
- Bo Liu et al., Best Student Paper @ UAI '15
for Finite sample analysis of proximal gradient TD algorithms - Tommy Boucher,
Analytical and Bioanalytical Chemistry Poster Award @ SciX '15
Outstanding Synthesis Project Award @ UMass' OAA '15
Congratulations to our recent alumni academic hires:
- George Konidaris, Duke University, Assistant professor of CS & ECE
- Scott Kuindersma, Harvard University, Assistant professor of Eng. & CS
- Scott Niekum, University of Texas at Austin, Assistant professor of CS