Diversity-based Deep Reinforcement Learning Towards Multidimensional Difficulty for Fighting Game AI

11/04/2022
by   Emily Halina, et al.
0

In fighting games, individual players of the same skill level often exhibit distinct strategies from one another through their gameplay. Despite this, the majority of AI agents for fighting games have only a single strategy for each "level" of difficulty. To make AI opponents more human-like, we'd ideally like to see multiple different strategies at each level of difficulty, a concept we refer to as "multidimensional" difficulty. In this paper, we introduce a diversity-based deep reinforcement learning approach for generating a set of agents of similar difficulty that utilize diverse strategies. We find this approach outperforms a baseline trained with specialized, human-authored reward functions in both diversity and performance.

READ FULL TEXT

page 2

page 3

research
12/24/2020

SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II

AlphaStar, the AI that reaches GrandMaster level in StarCraft II, is a r...
research
09/10/2019

Automatic difficulty management and testing in games using a framework based on behavior trees and genetic algorithms

The diversity of agent behaviors is an important topic for the quality o...
research
06/28/2023

Diversity is Strength: Mastering Football Full Game with Interactive Reinforcement Learning of Multiple AIs

Training AI with strong and rich strategies in multi-agent environments ...
research
08/29/2020

Predicting Game Difficulty and Churn Without Players

We propose a novel simulation model that is able to predict the per-leve...
research
09/06/2018

Emergence of Human-comparable Balancing Behaviors by Deep Reinforcement Learning

This paper presents a hierarchical framework based on deep reinforcement...
research
02/26/2019

Can Meta-Interpretive Learning outperform Deep Reinforcement Learning of Evaluable Game strategies?

World-class human players have been outperformed in a number of complex ...
research
06/17/2019

Manipulating the Difficulty of C-Tests

We propose two novel manipulation strategies for increasing and decreasi...

Please sign up or login with your details

Forgot password? Click here to reset