An exploration strategy for non-stationary opponents.
Pablo Hernandez-LealYusen ZhanMatthew E. TaylorLuis Enrique SucarEnrique Munoz de CotePublished in: Auton. Agents Multi Agent Syst. (2017)
Keyphrases
- non stationary
- exploration strategy
- unknown environments
- reinforcement learning
- locally optimal
- multi agent
- single agent
- multiple robots
- particle swarm optimisation
- empirical mode decomposition
- mobile robot
- free space
- markov decision problems
- machine learning
- game theory
- path planning
- nash equilibrium
- indoor environments
- ant colony