Reinforcement Learning Repository at UMass, Amherst

Topics in Reinforcement Learning

Reinforcement learning is an area of machine learning which addresses how an autonomous agent can learn long-term successful behavior through interaction with its environment. The term reinforcement learning has its roots in behavioral psychology, in particular to Pavlovian models of reward learning in animals. The modern theory of reinforcement learning, however, is much more influenced by mathematical theories of optimal control in operations research, such as dynamic programming.

Reinforcement learning differs from the more well-studied problem of supervised learning, in that the learner is not given input-output samples of the desired behavior. Rather, the learner is only supplied scalar feedback regarding the appropriateness of the actions, after they have been carried out. What makes this credit assignment problem even harder is that the feedback could be significantly delayed (e.g. win/loss in an extended game).

  • Applications to Robotics:   overview   publications
  • Average-reward/Undiscounted Methods: overview   publications
  • Distributed and Multi-Agent RL:   overview   publications
  • DP/MDP:   overview   publications
  • Function Approximation:   overview publications  
  • Hierarchical Methods:   overview   publications
  • Industrial Applications:   overview   publications
  • Neuro-biological RL:   overview   publications
  • Partially observable Problems:   overview   publications
  • Planning:   overview   publications
  • Policy-space Search Methods:   overview   publications
  • Shaping:   overview   publications
  • TD-learning:   overview   publications
  • Theoretical analysis:   overview   publications