Stable reinforcement learning with recurrent neural networks

This publication has 9 references indexed in Scilit:

• Robust Reinforcement Learning Control Using Integral Quadratic Constraints for Recurrent Neural Networks
  IEEE Transactions on Neural Networks, 2007
• A new continuously differentiable friction model for control systems design
  2006
• Handbook of Learning and Approximate Dynamic Programming
  2004
• Robust Control Systems
  2004
• A Course in Robust Control Theory
  2000
• Reinforcement Learning in Continuous Time and Space
  Neural Computation, 2000
• System analysis via integral quadratic constraints
  IEEE Transactions on Automatic Control, 1997
• Gradient calculations for dynamic recurrent neural networks: a survey
  IEEE Transactions on Neural Networks, 1995
• Reinforcement learning is direct adaptive optimal control
  IEEE Control Systems, 1992