Graduation Project Second Seminar Presentation. This seminar mainly aims justifies why we've used specific techniques and also, introduce our testing strategy
17. Why Reinforcement Learning Requires No Model Balance Exploration- Exploitation Applies Bootstrapping Used in the Revising Phase Sub-optimal policies
23. System Architecture I-Strategizer AI Engine : Online Case Based Planner I-StrategizerToWargus Case Based Reasoner EE Module Game State Goal Game State Expansion Module Plan Retriever Perception Module Retrieved Plan Plan to be adapted Adapted Plan Game State Plan Adaptor Case (Plan) Base Plan to be adapted Wargus (Game) Plan Game State Actions Executor Game Specific Actions Actions Executed Plan Execution Module Plan Reviser (RL Techniques) Plan Retainer Revised Plan Retained Plan Feedback Game Specific Feedback
28. References Santiago Ontanon, Ashwin Ram - On-Line Case based Planning– 2010 KristianJ.Hammond - Case-Based Planning - A Framework for planning from Experience - 1994 Book: Reinforcement Learning An Introduction – 1998 Matthew Molineaux, David W. Aha, & Philip Moore - Learning continuous action models in a real-time strategy environment - 2008 Book: AI Game Engine Programming - 2009