Faculty of Science
Reinforcement Learning and Artificial Intelligence
Home
Research
Auto TD
Autostep
Regularization in Reinforcement Learning
Nexting on a Reinforcement-Learning Robot
The Horde Architecture for Learning Knowledge Grounded in Sensorimotor Experience
Gradient Temporal-Difference Learning
Hybrid Gradient Temporal-Difference Learning
General Atari 2600 Game Playing
Creating Excitement at Glenrose
Reinforcement Learning for Adaptive Prosthetics
Representation Change for Learning
Transfer learning on the Critterbot
The Critterbot and Zephyr
Parameter-free Step-size Adaptation
Monte-Carlo Simulation Balancing (Computer Go)
Reinforcement Learning in the Brain
People
Group Photos
Graduate Students
Visitors
Alumni
Other RLAI Researchers
Events
RLAI Meeting
Tea Time Talks
Resources
RL FAQ
RLAI Library (Internal)
Software
Travel, Expenses, Reference Letters
Annual Reports
Sponsors
Contact
Positions
Home
Research
Auto TD
Autostep
Regularization in Reinforcement Learning
Nexting on a Reinforcement-Learning Robot
The Horde Architecture for Learning Knowledge Grounded in Sensorimotor Experience
Gradient Temporal-Difference Learning
Hybrid Gradient Temporal-Difference Learning
General Atari 2600 Game Playing
Creating Excitement at Glenrose
Reinforcement Learning for Adaptive Prosthetics
Representation Change for Learning
Transfer learning on the Critterbot
The Critterbot and Zephyr
Parameter-free Step-size Adaptation
Monte-Carlo Simulation Balancing (Computer Go)
Reinforcement Learning in the Brain
People
Group Photos
Graduate Students
Visitors
Alumni
Other RLAI Researchers
Events
RLAI Meeting
Tea Time Talks
Resources
RL FAQ
RLAI Library (Internal)
Software
Travel, Expenses, Reference Letters
Annual Reports
Sponsors
Contact
Positions
Group Photos
Group Photos
2018
2016
2007
2004
