A Case Study: Characterization of Performance Inconsistency for Reinforcement Learning on Flappy Bird Game.

Aidar Shakerimov Dmitriy Li Jurn-Gyu Park

Published in: ICTC (2021)

Keyphrases

reinforcement learning
function approximation
computer games
video games
case study
game theory
reinforcement learning algorithms
game play
nash equilibrium
state space

game theoretic
game playing
virtual world
learning algorithm
educational games
temporal difference
monte carlo tree search
role playing
pursuit evasion
optimal policy

optimal control
game design
machine learning
dynamic programming
multi agent
stochastic games
integrity checking
game players
two player games
bird species

multi agent reinforcement learning
reinforcement learning methods
temporal difference learning
learning agents
game development
serious games
test bed
markov decision processes
learning experience