Jonathan Sorg

Linear options

Satinder P. Singh, Jonathan Sorg, Satinder Singh, 2010, AAMAS.

Variance-Based Rewards for Approximate Bayesian Reinforcement Learning

Richard L. Lewis, Satinder P. Singh, Jonathan Sorg, 2010, UAI.

Internal Rewards Mitigate Agent Boundedness

Richard L. Lewis, Satinder P. Singh, Jonathan Sorg, 2010, ICML.

Intrinsically Motivated Reinforcement Learning: An Evolutionary Perspective

Richard L. Lewis, Andrew G. Barto, Satinder P. Singh, 2010, IEEE Transactions on Autonomous Mental Development.

Transfer via soft homomorphisms

Satinder P. Singh, Jonathan Sorg, Satinder Singh, 2009, AAMAS.

The Optimal Reward Problem: Designing Effective Reward for Bounded Agents

Satinder Singh Baveja, Jonathan Sorg, Jonathan Sorg, 2011 .

Reward Design via Online Gradient Ascent

Richard L. Lewis, Satinder P. Singh, Jonathan Sorg, 2010, NIPS.