Show simple item record

dc.contributor.authorHunt, Gareth David
dc.contributor.supervisorMihai Lazarescuen_US

We demonstrate a method of reinforcement learning that uses training in simulation. Our system generates an estimate of the potential reward and danger of each action as well as a measure of the uncertainty present in both. The system generates this by seeking out not only rewarding actions but also dangerous ones in the simulated training. During runtime our system is able to use this knowledge to avoid risks while accomplishing its tasks.

dc.publisherCurtin Universityen_US
dc.titleReinforcement Learning for Low Probability High Impact Risksen_US
curtin.departmentSchool of Electrical Engineering, Computing and Mathematical Scienceen_US
curtin.accessStatusOpen accessen_US
curtin.facultyScience and Engineeringen_US

Files in this item


This item appears in the following Collection(s)

Show simple item record