Enhanced rolling horizon evolution algorithm with opponent model learning: Results for the fighting game AI competition

Z Tang, Y Zhu, D Zhao, SM Lucas - IEEE Transactions on …, 2020‏ - ieeexplore.ieee.org
The Fighting Game AI Competition (FTGAIC) provides a challenging benchmark for two-
player video game artificial intelligence. The challenge arises from the large action space …

Evolving population method for real-time reinforcement learning

MJ Kim, JS Kim, CW Ahn - Expert Systems with Applications, 2023‏ - Elsevier
Reinforcement learning has recently been recognized as a promising means of machine
learning, but its applicability remains limited in real-time environment due to its short …

Adaptive traffic signal control system using composite reward architecture based deep reinforcement learning

ARM Jamil, KK Ganguly… - IET Intelligent Transport …, 2020‏ - Wiley Online Library
The increasing traffic congestion problem can be solved by an adaptive traffic signal control
(ATSC) system as it utilises real‐time traffic information to control traffic signals. Recently …

Time-varying weights in multi-reward architecture for deep reinforcement learning

M Xu, X Chen, Y She, Y **… - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
Deep Reinforcement Learning (DRL) has recently been focused on extracting more
knowledge from the reward signal to improve sample efficiency. The Multi-Reward …

A deep reinforcement learning blind AI in DareFightingICE

T Van Nguyen, X Dai, I Khan… - … IEEE Conference on …, 2022‏ - ieeexplore.ieee.org
This paper presents a deep reinforcement learning agent (AI) that uses sound as the input
on the DareFightingICE platform at the DareFightingICE Competition in IEEE CoG 2022. In …

AI Games and Algorithms: An Overview of Categories

S Jusoh, H Al Fawareh - 2023 15th International Conference on …, 2023‏ - ieeexplore.ieee.org
AI games are one of the growing fields along with the advancement of computing
technologies. Many computer games have been deployed as AI games. To the best of our …

Mastering fighting game using deep reinforcement learning with self-play

DW Kim, S Park, S Yang - 2020 IEEE Conference on Games …, 2020‏ - ieeexplore.ieee.org
One-on-one fighting game has played a role as a bridge between board game and real-time
simulation game in terms of research on game AI because it needs middle-level …

Surrogate-assisted Monte Carlo Tree Search for real-time video games

MJ Kim, D Lee, JS Kim, CW Ahn - Engineering Applications of Artificial …, 2024‏ - Elsevier
Abstract Monte Carlo Tree Search (MCTS) is a pronounced empirical search algorithm for
agent decision-making, especially when enhanced by Deep Learning (DL), in mastering …

A fighting game AI using highlight cues for generation of entertaining gameplay

R Ishii, S Ito, R Thawonmas… - 2019 IEEE Conference …, 2019‏ - ieeexplore.ieee.org
In this paper, we propose a fighting game AI that selects its actions from the perspective of
highlight generation using Monte-Carlo tree search (MCTS) with three highlight cues in the …

Evolving artificial neural networks for multi-objective tasks

S Künzel, S Meyer-Nieberg - … , EvoApplications 2018, Parma, Italy, April 4 …, 2018‏ - Springer
Neuroevolution represents a growing research field in Artificial and Computational
Intelligence. The adjustment of the network weights and the topology is usually based on a …