Goto

Collaborating Authors

 performance gradient

Rates of Convergence of Performance Gradient Estimates Using Function Approximation and Bias in Reinforcement Learning

Neural Information Processing Systems

We address two open theoretical questions in Policy Gradient Reinforcement Learning. The first concerns the efficacy of using function approximation to represent the state action value function,.

Rates of Convergence of Performance Gradient Estimates Using Function Approximation and Bias in Reinforcement Learning

Neural Information Processing Systems

We address two open theoretical questions in Policy Gradient Reinforcement Learning. The first concerns the efficacy of using function approximation to represent the state action value function,.

Rates of Convergence of Performance Gradient Estimates Using Function Approximation and Bias in Reinforcement Learning

Neural Information Processing Systems

We address two open theoretical questions in Policy Gradient Reinforcement Learning.The first concerns the efficacy of using function approximation torepresent the state action value function, .