Agent Evaluation Function Considering Airspace Dynamic Density.
Antônio Márcio Ferreira CrespoLi WeigangPublished in: Web Intelligence/IAT Workshops (2010)
Keyphrases
- evaluation function
- state action
- dynamic environments
- alpha beta pruning
- intelligent agents
- autonomous agents
- alpha beta
- general game playing
- two player games
- multi agent
- multiagent systems
- computer chess
- td learning
- monte carlo tree search
- branching factor
- temporal difference learning
- multi agent systems
- multiple agents
- optimality criterion
- human players
- heuristic function
- game tree search
- action selection