Sam Gershman
Wednesday 21st March 2018
Time:4.00pm
Ground Floor Seminar Room
25 Howland Street, London, W1T 4JG
A unifying probabilistic view of reinforcement learning
Two important ideas about reinforcement learning have emerged: (1) animals are probabilistic learners, tracking their uncertainty; and (2) animals acquire long-term reward predictions through reinforcement learning. Both of these ideas are normative, in the sense that they are derived from rational design principles. They are also descriptive, capturing a wide range of empirical phenomena that troubled earlier theories. I present a unifying framework encompassing probabilistic and reinforcement learning theories. Each perspective captures a different aspect of learning, and their synthesis offers insight into phenomena that neither perspective can explain on its own, including otherwise perplexing aspects of dopamine.