I graduated from the University of Alberta with a Ph.D. in Computing Science in 2015. During my doctoral studies I was advised by Richard Sutton, working in the RLAI lab.
Department of Computer Science
School of Informatics and Computing
CSCI-B 659: Reinforcement learning for Artificial Intelligence - Spring 2016
Reinforcement Learning, Robotics, Knowledge Representation and
My research focuses on the problem of Artifical Intelligence,
specifically how to replicate or simulate human level intelligence in
real and simulated agents. My research program explores how the
problem of intelligence can be modelled as a reinforcement learning
agent interacting with some unknown enviroment, learning from a scalar
reward signal rather than explicit feedback. My contributions include
new algorithms for reinforcement learning, and large-scale
demonstrations of learning on mobile robots.
My current CV can be found
Modayil, J., White, A., Sutton, R. S. (2014). Multi-timescale Nexting
in a Reinforcement Learning Robot. Adaptive Behavior, 22(2):146--160.
Whiteson, S., Tanner, B., & White, A. (2010). The reinforcement
learning competitions. AI Magazine, 31(2): 81--94.
Tanner, B., & White, A. (2009). RL-Glue: Language-independent software for reinforcement-learning experiments. The Journal of Machine Learning Research, 10: 2133--2136.
Sherstan, C., Machado, M., ,White, A., Patrick P. (2016). Introspective Agents: Confidence Measures for General Value
Functions, Artificial General Intelligence (AGI).
White, A., White M. (2016). Investigating practical linear temporal difference learning. In International Conference on Autonomous Agents and MultiAgent Systems (AAMAS). [ CODE ]
White, M., White A. (2016) Adapting the trace parameter in reinforcement learning, In International Conference on Autonomous Agents and MultiAgent Systems (AAMAS).
White, A., Modayil, J., & Sutton, R. S. (2012). Scaling
life-long off-policy learning. In the IEEE International Conference on Development and Learning and
Epigenetic Robotics, 1--6.
[paper of distinction award]
Modayil, J., White, A., Pilarski, P. M., & Sutton, R. S. (2012). Acquiring a broad
range of empirical knowledge in real time by temporal-difference
learning. In the IEEE International Conference on Systems,
Man, and Cybernetics, 1903--1910.
Modayil, J., White, A., Sutton, R. S. (2012). Multi-timescale Nexting
in a Reinforcement Learning Robot. Presented at the 2012 International
Conference on Adaptive Behaviour, Odense, Denmark. To appear in: SAB
12, LNAI 7426, pp. 299-309, T. Ziemke, C. Balkenius, and J. Hallam,
Eds., Springer Heidelberg.
Sutton, R. S., Modayil, J., Delp, M., Degris, T., Pilarski, P. M.,
White, A., & Precup, D. (2011). Horde: A
scalable real-time architecture for learning knowledge from
unsupervised sensorimotor interaction. In The 10th
International Conference on Autonomous Agents and Multiagent
Systems: 2, 761--768.
White, M., & White, A. (2010). Interval
estimation for reinforcement-learning algorithms in continuous-state
domains. In Advances in Neural Information Processing Systems, 2433--2441.
Sturtevant, N. R., & White, A. M. (2007). Feature
construction for reinforcement learning in hearts. In
Computers and Games . Springer Berlin Heidelberg, 122--134
Other published works
White, A., & Sutton, R. S. (2014). GQ (λ) Quick Reference Guide.
White, A., Modayil, J., & Sutton, R. S. (2014). Surprise and
curiosity for big data robotics. In Workshops at the
Twenty-Eighth AAAI Conference on Artificial Intelligence.
Modayil, J., White, A., Pilarski, P. M., Sutton, R. S. (2012). Acquiring
Diverse Predictive Knowledge in Real Time by Temporal-difference
Learning. International Workshop on Evolutionary and
Reinforcement Learning for Autonomous Robot Systems, Montpellier, France.
[Best paper award]
Modayil, J., Pilarski, P., White, A., Degris, T., & Sutton,
R. (2010). Off-policy knowledge maintenance for robots. In Proceedings
of Robotics Science and Systems Workshop (Towards Closing the Loop:
Active Learning for Robotics) : 55.
White, A. (2015) Developing a predictive approach to knowledge. Doctoral thesis, University of Alberta.
White, A. (2006) A standard system for benchmarking in reinforcement
learning. Master's thesis, University of Alberta.
google scholar page for a list of my
publications that Google knows about.
Office: 201I Lindley Hall
School of Informatics and Computing