TY - GEN
T1 - Online evolution for multi-action adversarial games
AU - Justesen, Niels Orsleff
AU - Mahlmann, Tobias
AU - Togelius, Julian
PY - 2016/3/15
Y1 - 2016/3/15
N2 - We present Online Evolution, a novel method for playing turn-based multi-action adversarial games. Such games, which include most strategy games, have extremely high branching factors due to each turn having multiple actions. In Online Evolution, an evolutionary algorithm is used to evolve the combination of atomic actions that make up a single move, with a state evaluation function used for fitness. We implement Online Evolution for the turn-based multi-action game Hero Academy and compare it with a standard Monte Carlo Tree Search implementation as well as two types of greedy algorithms. Online Evolution is shown to outperform these methods by a large margin. This shows that evolutionary planning on the level of a single move can be very effective for this sort of problems.
AB - We present Online Evolution, a novel method for playing turn-based multi-action adversarial games. Such games, which include most strategy games, have extremely high branching factors due to each turn having multiple actions. In Online Evolution, an evolutionary algorithm is used to evolve the combination of atomic actions that make up a single move, with a state evaluation function used for fitness. We implement Online Evolution for the turn-based multi-action game Hero Academy and compare it with a standard Monte Carlo Tree Search implementation as well as two types of greedy algorithms. Online Evolution is shown to outperform these methods by a large margin. This shows that evolutionary planning on the level of a single move can be very effective for this sort of problems.
U2 - 10.1007/978-3-319-31204-0_38
DO - 10.1007/978-3-319-31204-0_38
M3 - Article in proceedings
T3 - Lecture Notes in Computer Science
SP - 590
EP - 603
BT - Applications of Evolutionary Computation
PB - Springer Publishing Company
ER -