# Temporal difference learning

## Papers overview

Semantic Scholar uses AI to extract papers important to this topic.

2016

2016

- Journal of Machine Learning Research
- 2016

The temporal-difference methods TD(Î») and Sarsa(Î») form a core part of modern reinforcement learning. Their appeal comes fromâ€¦Â (More)

Is this relevant?

2010

2010

- NIPS
- 2010

We propose a new approach to value function approximation which combines linear temporal difference reinforcement learning withâ€¦Â (More)

Is this relevant?

Highly Cited

2009

Highly Cited

2009

- ICML
- 2009

We consider the task of reinforcement learning with linear value function approximation. Temporal difference algorithms, and inâ€¦Â (More)

Is this relevant?

2008

2008

- ICML
- 2008

This paper extends many of the recent popular policy evaluation algorithms to a generalized framework that includes least-squaresâ€¦Â (More)

Is this relevant?

2006

2006

- ICML
- 2006

We introduce relational temporal difference learning as an effective approach to solving multi-agent Markov decision problemsâ€¦Â (More)

Is this relevant?

Highly Cited

2002

Highly Cited

2002

- Machine Learning
- 2002

TD.Î»/ is a popular family of algorithms for approximate policy evaluation in large MDPs. TD.Î»/ works by incrementally updatingâ€¦Â (More)

Is this relevant?

Highly Cited

1999

Highly Cited

1999

- ICML
- 1999

Excerpted from:Boyan, Justin. Learning Evaluation Functions for Global Op timization. Ph.D. thesis, Carnegie Mellon Universityâ€¦Â (More)

Is this relevant?

Highly Cited

1999

Highly Cited

1999

- Automatica
- 1999

We propose a variant of temporal-di!erence learning that approximates average and di!erential costs of an irreducible aperiodicâ€¦Â (More)

Is this relevant?

Highly Cited

1996

Highly Cited

1996

- Machine Learning
- 1996

We introduce two new temporal difference (TD) algorithms based on the theory of linear least-squares function approximation. Weâ€¦Â (More)

Is this relevant?

Highly Cited

1996

Highly Cited

1996

- 1996

We discuss the temporal-difference learning algorithm, as applied to approximating the cost-to-go function of an infinite-horizonâ€¦Â (More)

Is this relevant?