Rolling Horizon NEAT for General Video Game Playing
| Autor: | Muhammad Sajid Alam, Diego Perez-Liebana, Raluca D. Gaina |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Sequence Artificial neural network Computer Science - Artificial Intelligence Computer science business.industry Evolutionary algorithm Computer Science - Neural and Evolutionary Computing 0102 computer and information sciences 02 engineering and technology 01 natural sciences General video game playing Artificial Intelligence (cs.AI) Action (philosophy) 010201 computation theory & mathematics 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Neural and Evolutionary Computing (cs.NE) Neuroevolution of augmenting topologies Artificial intelligence State (computer science) Rolling horizon business |
| Zdroj: | CoG |
| DOI: | 10.1109/cog47356.2020.9231606 |
| Popis: | This paper presents a new Statistical Forward Planning (SFP) method, Rolling Horizon NeuroEvolution of Augmenting Topologies (rhNEAT). Unlike traditional Rolling Horizon Evolution, where an evolutionary algorithm is in charge of evolving a sequence of actions, rhNEAT evolves weights and connections of a neural network in real-time, planning several steps ahead before returning an action to execute in the game. Different versions of the algorithm are explored in a collection of 20 GVGAI games, and compared with other SFP methods and state of the art results. Although results are overall not better than other SFP methods, the nature of rhNEAT to adapt to changing game features has allowed to establish new state of the art records in games that other methods have traditionally struggled with. The algorithm proposed here is general and introduces a new way of representing information within rolling horizon evolution techniques. 8 pages, 5 figures, accepted for publication in IEEE Conference on Games (CoG) 2020 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|