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

• URL: http://arxiv.org/abs/2211.02759v1
• Date: Fri, 4 Nov 2022 21:49:52 GMT
• Title: Diversity-based Deep Reinforcement Learning Towards Multidimensional Difficulty for Fighting Game AI
• Authors: Emily Halina, Matthew Guzdial
• Abstract summary: We introduce a diversity-based deep reinforcement learning approach for generating a set of agents of similar difficulty. We find this approach outperforms a baseline trained with specialized, human-authored reward functions in both diversity and performance.
• Score: 0.9645196221785693
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Personalized Dynamic Difficulty Adjustment -- Imitation Learning Meets Reinforcement Learning [44.99833362998488]
  In this work, we explore balancing game difficulty using machine learning-based agents to challenge players based on their current behavior. This is achieved by a combination of two agents, in which one learns to imitate the player, while the second is trained to beat the first. In our demo, we investigate the proposed framework for personalized dynamic difficulty adjustment of AI agents in the context of the fighting game AI competition.
  arXiv  Detail & Related papers  (2024-08-13T11:24:12Z)
• Reinforcement Learning for High-Level Strategic Control in Tower Defense Games [47.618236610219554]
  In strategy games, one of the most important aspects of game design is maintaining a sense of challenge for players. We propose an automated approach that combines traditional scripted methods with reinforcement learning. Results show that combining a learned approach, such as reinforcement learning, with a scripted AI produces a higher-performing and more robust agent than using only AI.
  arXiv  Detail & Related papers  (2024-06-12T08:06:31Z)
• DanZero+: Dominating the GuanDan Game through Reinforcement Learning [95.90682269990705]
  We develop an AI program for an exceptionally complex and popular card game called GuanDan. We first put forward an AI program named DanZero for this game. In order to further enhance the AI's capabilities, we apply policy-based reinforcement learning algorithm to GuanDan.
  arXiv  Detail & Related papers  (2023-12-05T08:07:32Z)
• All by Myself: Learning Individualized Competitive Behaviour with a Contrastive Reinforcement Learning optimization [57.615269148301515]
  In a competitive game scenario, a set of agents have to learn decisions that maximize their goals and minimize their adversaries' goals at the same time. We propose a novel model composed of three neural layers that learn a representation of a competitive game, learn how to map the strategy of specific opponents, and how to disrupt them. Our experiments demonstrate that our model achieves better performance when playing against offline, online, and competitive-specific models, in particular when playing against the same opponent multiple times.
  arXiv  Detail & Related papers  (2023-10-02T08:11:07Z)
• Pick Your Battles: Interaction Graphs as Population-Level Objectives for Strategic Diversity [49.68758494467258]
  We study how to construct diverse populations of agents by carefully structuring how individuals within a population interact. Our approach is based on interaction graphs, which control the flow of information between agents during training. We provide evidence for the importance of diversity in multi-agent training and analyse the effect of applying different interaction graphs on the training trajectories, diversity and performance of populations in a range of games.
  arXiv  Detail & Related papers  (2021-10-08T11:29:52Z)
• Identification of Play Styles in Universal Fighting Engine [0.0]
  We show how an automated procedure can be used to compare play styles of individual AI- and human-controlled characters. We also show how it can be used to assess human-likeness and diversity of game participants.
  arXiv  Detail & Related papers  (2021-08-08T10:06:16Z)
• Generating Diverse and Competitive Play-Styles for Strategy Games [58.896302717975445]
  We propose Portfolio Monte Carlo Tree Search with Progressive Unpruning for playing a turn-based strategy game (Tribes) We show how it can be parameterized so a quality-diversity algorithm (MAP-Elites) is used to achieve different play-styles while keeping a competitive level of play. Our results show that this algorithm is capable of achieving these goals even for an extensive collection of game levels beyond those used for training.
  arXiv  Detail & Related papers  (2021-04-17T20:33:24Z)
• Multi-AI competing and winning against humans in iterated Rock-Paper-Scissors game [4.2124879433151605]
  We use an AI algorithm based on Markov Models of one fixed memory length to compete against humans in an iterated Rock Paper Scissors game. We develop an architecture of multi-AI with changeable parameters to adapt to different competition strategies. Our strategy could win against more than 95% of human opponents.
  arXiv  Detail & Related papers  (2020-03-15T06:39:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.