|
|
|
|
|
|
Help | Seminars List | Add Seminar | Edit Seminars | Tips for organisers | RSS | ics Calendar | Search | Send comments about this website to seminar-master@cecs.anu.edu.au
Contact: Michelle.Moravec@anu.edu.au CS PHD MONITORING
Continuous Reinforcement Learning Applied to Interactive Computer GamesMr Matthew Robards (School of Computer Science, CECS)DATE: 2009-09-24 TIME: 11:15:00 - 11:45:00 LOCATION: RSISE Seminar Room, ground floor, building 115, cnr. North and Daley Roads, ANU ABSTRACT: Reinforcement learning is an unsupervised form of learning in which the agent learns through interaction with its environment. Typically the reinforcement learning agent acts in a Markov Decision Process (MDP), defined through a state action reward tuple. Traditionally reinforcement learning agents stored state-action values tabularly, which represent the expected return of taking a specific action in the current state. In this talk I will begin by introducing the notion of the MDP. I will then move onto the less studied problem of continuous state action reinforcement learning with function approximation and discuss its application to interactive computer games.
|