The Divergence of Reinforcement Learning Algorithms with Value-Iteration and Function Approximation

Details The Divergence of Reinforcement Learning Algorithms with Value-Iteration and Function Approximation The Divergence of Reinforcement Learning Algorithms with Value-Iteration and Function Approximation

2011-07-22

arxiv.org/abs/1107.4606v1

Computer Science

Learning

Scientific paper

This paper gives specific divergence examples of value-iteration for several major Reinforcement Learning and Adaptive Dynamic Programming algorithms, when using a function approximator for the value function. These divergence examples differ from previous divergence examples in the literature, in that they are applicable for a greedy policy, i.e. in a "value iteration" scenario. Perhaps surprisingly, with a greedy policy, it is also possible to get divergence for the algorithms TD(1) and Sarsa(1). In addition to these divergences, we also achieve divergence for the Adaptive Dynamic Programming algorithms HDP, DHP and GDHP.

Affiliated with

Also associated with

No associations

Rating

The Divergence of Reinforcement Learning Algorithms with Value-Iteration and Function Approximation does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with The Divergence of Reinforcement Learning Algorithms with Value-Iteration and Function Approximation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and The Divergence of Reinforcement Learning Algorithms with Value-Iteration and Function Approximation will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-677383