Mastering Asymmetrical Multiplayer Game with Multi-Agent Asymmetric-Evolution Reinforcement Learning

• URL: http://arxiv.org/abs/2304.10124v1
• Date: Thu, 20 Apr 2023 07:14:32 GMT
• Title: Mastering Asymmetrical Multiplayer Game with Multi-Agent Asymmetric-Evolution Reinforcement Learning
• Authors: Chenglu Sun, Yichi Zhang, Yu Zhang, Ziling Lu, Jingbin Liu, Sijia Xu and Weidong Zhang (AI Lab, Netease)
• Abstract summary: Asymmetrical multiplayer (AMP) game is a popular game genre which involves multiple types of agents competing or collaborating in the game. It is difficult to train powerful agents that can defeat top human players in AMP games by typical self-play training method because of unbalancing characteristics in their asymmetrical environments. We propose asymmetric-evolution training (AET), a novel multi-agent reinforcement learning framework that can train multiple kinds of agents simultaneously in AMP game.
• Score: 8.628547849796615
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Asymmetrical multiplayer (AMP) game is a popular game genre which involves multiple types of agents competing or collaborating with each other in the game. It is difficult to train powerful agents that can defeat top human players in AMP games by typical self-play training method because of unbalancing characteristics in their asymmetrical environments. We propose asymmetric-evolution training (AET), a novel multi-agent reinforcement learning framework that can train multiple kinds of agents simultaneously in AMP game. We designed adaptive data adjustment (ADA) and environment randomization (ER) to optimize the AET process. We tested our method in a complex AMP game named Tom \& Jerry, and our AIs trained without using any human data can achieve a win rate of 98.5% against top human players over 65 matches. The ablation experiments indicated that the proposed modules are beneficial to the framework.

Related papers

• Multi-Agent Training for Pommerman: Curriculum Learning and Population-based Self-Play Approach [11.740631954398292]
  Pommerman is an ideal benchmark for multi-agent training, providing a battleground for two teams with communication capabilities among allied agents. This study introduces a system designed to train multi-agent systems to play Pommerman using a combination of curriculum learning and population-based self-play.
  arXiv  Detail & Related papers  (2024-06-30T11:14:29Z)
• Symmetry-Breaking Augmentations for Ad Hoc Teamwork [10.014956508924842]
  In many collaborative settings, artificial intelligence (AI) agents must be able to adapt to new teammates that use unknown or previously unobserved strategies. We introduce symmetry-breaking augmentations (SBA), which increases diversity in the behaviour of training teammates by applying a symmetry-flipping operation. We demonstrate this experimentally in two settings, and show that our approach improves upon previous ad hoc teamwork results in the challenging card game Hanabi.
  arXiv  Detail & Related papers  (2024-02-15T14:49:28Z)
• Toward Human-AI Alignment in Large-Scale Multi-Player Games [24.784173202415687]
  We analyze extensive human gameplay data from Xbox's Bleeding Edge (100K+ games) We find that while human players exhibit variability in fight-flight and explore-exploit behavior, AI players tend towards uniformity. These stark differences underscore the need for interpretable evaluation, design, and integration of AI in human-aligned applications.
  arXiv  Detail & Related papers  (2024-02-05T22:55:33Z)
• ProAgent: Building Proactive Cooperative Agents with Large Language Models [89.53040828210945]
  ProAgent is a novel framework that harnesses large language models to create proactive agents. ProAgent can analyze the present state, and infer the intentions of teammates from observations. ProAgent exhibits a high degree of modularity and interpretability, making it easily integrated into various coordination scenarios.
  arXiv  Detail & Related papers  (2023-08-22T10:36:56Z)
• Generating Personas for Games with Multimodal Adversarial Imitation Learning [47.70823327747952]
  Reinforcement learning has been widely successful in producing agents capable of playing games at a human level. Going beyond reinforcement learning is necessary to model a wide range of human playstyles. This paper presents a novel imitation learning approach to generate multiple persona policies for playtesting.
  arXiv  Detail & Related papers  (2023-08-15T06:58:19Z)
• Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning [95.78031053296513]
  No-press Diplomacy is a complex strategy game involving both cooperation and competition. We introduce a planning algorithm we call DiL-piKL that regularizes a reward-maximizing policy toward a human imitation-learned policy. We show that DiL-piKL can be extended into a self-play reinforcement learning algorithm we call RL-DiL-piKL.
  arXiv  Detail & Related papers  (2022-10-11T14:47:35Z)
• Multi-Game Decision Transformers [49.257185338595434]
  We show that a single transformer-based model can play a suite of up to 46 Atari games simultaneously at close-to-human performance. We compare several approaches in this multi-game setting, such as online and offline RL methods and behavioral cloning. We find that our Multi-Game Decision Transformer models offer the best scalability and performance.
  arXiv  Detail & Related papers  (2022-05-30T16:55:38Z)
• Mimicking Playstyle by Adapting Parameterized Behavior Trees in RTS Games [0.0]
  Behavior Trees (BTs) impacted the field of Artificial Intelligence (AI) in games. BTs forced complexity of handcrafted BTs to became barely-tractable and error-prone. Recent trends in the field focused on automatic creation of AI-agents. We present a novel approach to semi-automatic construction of AI-agents, that mimic and generalize given human gameplays.
  arXiv  Detail & Related papers  (2021-11-23T20:36:28Z)
• Policy Fusion for Adaptive and Customizable Reinforcement Learning Agents [137.86426963572214]
  We show how to combine distinct behavioral policies to obtain a meaningful "fusion" policy. We propose four different policy fusion methods for combining pre-trained policies. We provide several practical examples and use-cases for how these methods are indeed useful for video game production and designers.
  arXiv  Detail & Related papers  (2021-04-21T16:08:44Z)
• Multi-Agent Collaboration via Reward Attribution Decomposition [75.36911959491228]
  We propose Collaborative Q-learning (CollaQ) that achieves state-of-the-art performance in the StarCraft multi-agent challenge. CollaQ is evaluated on various StarCraft Attribution maps and shows that it outperforms existing state-of-the-art techniques.
  arXiv  Detail & Related papers  (2020-10-16T17:42:11Z)

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.