Risk-Sensitive Reinforcement Learning Applied to Control under Constraints

Details Risk-Sensitive Reinforcement Learning Applied to Control under Constraints Risk-Sensitive Reinforcement Learning Applied to Control under Constraints

2011-09-09

arxiv.org/abs/1109.2147v1

Journal Of Artificial Intelligence Research, Volume 24, pages 81-108, 2005

Computer Science

Learning

Scientific paper

10.1613/jair.1666

In this paper, we consider Markov Decision Processes (MDPs) with error states. Error states are those states entering which is undesirable or dangerous. We define the risk with respect to a policy as the probability of entering such a state when the policy is pursued. We consider the problem of finding good policies whose risk is smaller than some user-specified threshold, and formalize it as a constrained MDP with two criteria. The first criterion corresponds to the value function originally given. We will show that the risk can be formulated as a second criterion function based on a cumulative return, whose definition is independent of the original value function. We present a model free, heuristic reinforcement learning algorithm that aims at finding good deterministic policies. It is based on weighting the original value function and the risk. The weight parameter is adapted in order to find a feasible solution for the constrained problem that has a good performance with respect to the value function. The algorithm was successfully applied to the control of a feed tank with stochastic inflows that lies upstream of a distillation column. This control task was originally formulated as an optimal control problem with chance constraints, and it was solved under certain assumptions on the model to obtain an optimal solution. The power of our learning algorithm is that it can be used even when some of these restrictive assumptions are relaxed.

Affiliated with

Also associated with

No associations

Rating

Risk-Sensitive Reinforcement Learning Applied to Control under Constraints 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 Risk-Sensitive Reinforcement Learning Applied to Control under Constraints, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Risk-Sensitive Reinforcement Learning Applied to Control under Constraints will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-38115