AUGMENTING SELF-LEARNING AGENT IN FIRST-PERSON SHOOTER GAME USING REINFORCEMENT LEARNING
Date
2023-04-30
Journal Title
Journal ISSN
Volume Title
Publisher
I.O.E. Pulchowk Campus
Abstract
This group project highlights the effectiveness of utilizing reinforcement learning (RL) along
with the Proximal Policy Optimization (PPO) algorithm to train an agent to play aWolfenstein3Dlike
game with multiple levels. The agent exhibited exceptional performance in relation to
reward, time efficiency, and overall effectiveness. An in-depth analysis of its performance
indicated marked enhancements in the reward curves, strategic navigation throughout the
game levels, and expeditious completion of each level. The study highlights the potential of
RL and PPO for training agents in complex video games with multiple levels, as well as in
other applications such as agent-based modeling and machine learning.
Description
Reinforcement Learning(RL) is a powerful machine learning technique in which an agent
learns to solve a problem by interacting with its environment. Through a system of rewards
and punishments, agents learn to make decisions that maximize rewards and minimize negative
consequences. RL is rapidly becoming a prominent area of research, with a growing
number of applications in a wide range of fields .
Keywords
Reinforcement Learning,, Deep Reinforcement Learning,, Curriculum Learning