Reinforcement Learning by Value Gradients

  title={Reinforcement Learning by Value Gradients},
  author={Michael Fairbank},
The concept of the value-gradient is introduced and developed in the context of reinforcement learning, for deterministic episodic control problems that use a function approximator and have a continuous state space. It is shown that by learning the valuegradients, instead of just the values themselves, exploration or stochastic behaviour is no longer needed to find locally optimal trajectories. This is the main motivation for using value-gradients, and it is argued that learning the value… CONTINUE READING