Temporal difference learning

Known as: TD lambda, Temporal-difference learning, Temporal Difference 
Temporal difference (TD) learning is a prediction-based machine learning method. It has primarily been used for the reinforcement learning problem… (More)
Wikipedia

Papers overview

Semantic Scholar uses AI to extract papers important to this topic.
2016
2016
The temporal-difference methods TD(λ) and Sarsa(λ) form a core part of modern reinforcement learning. Their appeal comes from… (More)
  • figure 1
  • figure 2
  • figure 3
  • figure 4
  • figure 6
Is this relevant?
2010
2010
We propose a new approach to value function approximation which combines linear temporal difference reinforcement learning with… (More)
  • figure 1
Is this relevant?
Highly Cited
2009
Highly Cited
2009
We consider the task of reinforcement learning with linear value function approximation. Temporal difference algorithms, and in… (More)
  • figure 2
  • figure 3
  • table 1
Is this relevant?
2008
2008
This paper extends many of the recent popular policy evaluation algorithms to a generalized framework that includes least-squares… (More)
  • figure 1
  • figure 2
  • figure 3
  • figure 5
  • figure 4
Is this relevant?
2006
2006
We introduce relational temporal difference learning as an effective approach to solving multi-agent Markov decision problems… (More)
  • figure 1
  • table 3
  • figure 2
  • table 4
Is this relevant?
Highly Cited
2002
Highly Cited
2002
TD.λ/ is a popular family of algorithms for approximate policy evaluation in large MDPs. TD.λ/ works by incrementally updating… (More)
  • figure 1
  • table 1
  • figure 3
  • figure 4
  • figure 5
Is this relevant?
Highly Cited
1999
Highly Cited
1999
Excerpted from:Boyan, Justin. Learning Evaluation Functions for Global Op timization. Ph.D. thesis, Carnegie Mellon University… (More)
  • figure 1
  • figure 2
  • figure 3
Is this relevant?
Highly Cited
1999
Highly Cited
1999
We propose a variant of temporal-di!erence learning that approximates average and di!erential costs of an irreducible aperiodic… (More)
Is this relevant?
Highly Cited
1996
Highly Cited
1996
We introduce two new temporal difference (TD) algorithms based on the theory of linear least-squares function approximation. We… (More)
Is this relevant?
Highly Cited
1996
Highly Cited
1996
We discuss the temporal-difference learning algorithm, as applied to approximating the cost-to-go function of an infinite-horizon… (More)
Is this relevant?