Reinforcement Learning Main Page

Click here for all Reinforcement Learning papers by Satinder Singh.

I have long been rethinking all of the three basic aspects of RL problem formulations: state, action, and reward.

  1. Rethinking state. This effort has led to the projects on Predictive State Representations / Spectral Learning.
  2. Rethinking action. My own effort on this started with my early work on temporally abstract actions in RL that led to later work on options.
  3. Rethinking reward. This effort has led to the projects on Optimal Rewards / Intrinsically Motivated RL.

A recent research effort is on combining Deep Learning and Reinforcement Learning.

Some older RL-papers categorizations include:

  1. Theoretical Results in RL.
  2. Applications.