20 citations · 39 across the 9 of their papers we have counts for
Showing 2011Show all
2 papers · 1 filter
cs.LG2011★ 1 cited
The Divergence of Reinforcement Learning Algorithms with Value-Iteration and Function Approximation
Michael Fairbank, Eduardo Alonso
This paper gives specific divergence examples of value-iteration for several major Reinforcement Learning and Adaptive Dynamic Programming algorithms, when using a function approxi…
cs.LG2011★ 10 cited
The Local Optimality of Reinforcement Learning by Value Gradients, and its Relationship to Policy Gradient Learning
Michael Fairbank, Eduardo Alonso
In this theoretical paper we are concerned with the problem of learning a value function by a smooth general function approximator, to solve a deterministic episodic control proble…