Leveraging Reinforcement Learning Techniques for Effective Policy Adoption and Validation

by   Nikki Lijing Kuang, et al.

Rewards and punishments in different forms are pervasive and present in a wide variety of decision-making scenarios. By observing the outcome of a sufficient number of repeated trials, one would gradually learn the value and usefulness of a particular policy or strategy. However, in a given environment, the outcomes resulting from different trials are subject to chance influence and variations. In learning about the usefulness of a given policy, significant costs are involved in systematically undertaking the sequential trials; therefore, in most learning episodes, one would wish to keep the cost within bounds by adopting learning stopping rules. In this paper, we examine the deployment of different stopping strategies in given learning environments which vary from highly stringent for mission critical operations to highly tolerant for non-mission critical operations, and emphasis is placed on the former with particular application to aviation safety. In policy evaluation, two sequential phases of learning are identified, and we describe the outcomes variations using a probabilistic model, with closedform expressions obtained for the key measures of performance. Decision rules that map the trial observations to policy choices are also formulated. In addition, simulation experiments are performed, which corroborate the validity of the theoretical results.


page 1

page 2

page 3

page 4


Improving Gradient Estimation by Incorporating Sensor Data

An efficient policy search algorithm should estimate the local gradient ...

Reliable Off-policy Evaluation for Reinforcement Learning

In a sequential decision-making problem, off-policy evaluation (OPE) est...

Joint modelling of longitudinal and time-to-event data applied to group sequential clinical trials

Often in Phase 3 clinical trials measuring a long-term time-to-event end...

Bayesian Persuasion in Sequential Trials

We consider a Bayesian persuasion or information design problem where th...

Pre-emptive learning-to-defer for sequential medical decision-making under uncertainty

We propose SLTD (`Sequential Learning-to-Defer') a framework for learnin...

Leveraging Multiple Environments for Learning and Decision Making: a Dismantling Use Case

Learning is usually performed by observing real robot executions. Physic...

Interpretable Off-Policy Evaluation in Reinforcement Learning by Highlighting Influential Transitions

Off-policy evaluation in reinforcement learning offers the chance of usi...

Please sign up or login with your details

Forgot password? Click here to reset