The Local Optimality of Reinforcement Learning by Value Gradients, and its Relationship to Policy Gradient Learning

Details The Local Optimality of Reinforcement Learning by Value Gradients, and its Relationship to Policy Gradient Learning The Local Optimality of Reinforcement Learning by Value Gradients, and its Relationship to Policy Gradient Learning

2011-01-02

arxiv.org/abs/1101.0428v1

Computer Science

Learning

Scientific paper

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 problem in a large continuous state space. It is shown that learning the gradient of the value-function at every point along a trajectory generated by a greedy policy is a sufficient condition for the trajectory to be locally extremal, and often locally optimal, and we argue that this brings greater efficiency to value-function learning. This contrasts to traditional value-function learning in which the value-function must be learnt over the whole of state space. It is also proven that policy-gradient learning applied to a greedy policy on a value-function produces a weight update equivalent to a value-gradient weight update, which provides a surprising connection between these two alternative paradigms of reinforcement learning, and a convergence proof for control problems with a value function represented by a general smooth function approximator.

Affiliated with

Also associated with

No associations

Rating

The Local Optimality of Reinforcement Learning by Value Gradients, and its Relationship to Policy Gradient Learning 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 Local Optimality of Reinforcement Learning by Value Gradients, and its Relationship to Policy Gradient Learning, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and The Local Optimality of Reinforcement Learning by Value Gradients, and its Relationship to Policy Gradient Learning will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-237956