Corpus ID: 2029607

Transfer Learning via Inter-Task Mappings for Temporal Difference Learning

  title={Transfer Learning via Inter-Task Mappings for Temporal Difference Learning},
  author={Matthew E. Taylor and P. Stone and Y. Liu},
  journal={J. Mach. Learn. Res.},
  • Matthew E. Taylor, P. Stone, Y. Liu
  • Published 2007
  • Computer Science
  • J. Mach. Learn. Res.
  • Temporal difference (TD) learning (Sutton and Barto, 1998) has become a popular reinforcement learning technique in recent years. TD methods, relying on function approximators to generalize learning to novel situations, have had some experimental successes and have been shown to exhibit some desirable properties in theory, but the most basic algorithms have often been found slow in practice. This empirical result has motivated the development of many methods that speed up reinforcement learning… CONTINUE READING
    Autonomous transfer for reinforcement learning
    • 103
    • PDF
    Learning modular neural network policies for multi-task and multi-robot transfer
    • 172
    • PDF
    Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning
    • 109
    • PDF
    A comprehensive survey on safe reinforcement learning
    • 433
    • PDF
    Transfer in Reinforcement Learning: A Framework and a Survey
    • 135
    • PDF
    Transfer in Reinforcement Learning via Shared Features
    • 96
    • PDF
    Transfer of samples in batch reinforcement learning
    • 105
    • Highly Influenced
    • PDF


    Publications referenced by this paper.
    On-line Q-learning using connectionist systems
    • 1,159
    • Highly Influential
    Markov Decision Processes: Discrete Stochastic Dynamic Programming
    • 10,238
    • Highly Influential
    TD-Gammon, a Self-Teaching Backgammon Program, Achieves Master-Level Play
    • 729
    • Highly Influential
    • PDF
    Analogical problem solving
    • 2,259
    • PDF
    Cross-domain transfer for reinforcement learning
    • 150
    • PDF
    Science And Human Behavior
    • 6,778
    • PDF
    Reward Functions for Accelerated Learning
    • 399
    • PDF
    Reinforcement learning with replacing eligibility traces
    • 394
    • PDF