The Successor Representation and Temporal Context

  title={The Successor Representation and Temporal Context},
  author={Samuel J Gershman and Christopher D. Moore and Michael T. Todd and Kenneth A. Norman and Per B. Sederberg},
  journal={Neural Computation},
The successor representation was introduced into reinforcement learning by Dayan (1993) as a means of facilitating generalization between states with similar successors. Although reinforcement learning in general has been used extensively as a model of psychological and neural processes, the psychological validity of the successor representation has yet to be explored. An interesting possibility is that the successor representation can be used not only for reinforcement learning but for… CONTINUE READING
Highly Cited
This paper has 42 citations. REVIEW CITATIONS
22 Citations
58 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 22 extracted citations


Publications referenced by this paper.
Showing 1-10 of 58 references

Temporal Difference Learning: Eligibility Traces and the Successor Representation for Actions

  • L. White
  • Unpublished master’s thesis, Department of…
  • 1995
Highly Influential
6 Excerpts

Similar Papers

Loading similar papers…