mlsanityData to 14 Oct 2026

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

arXiv 2304.10124 ↗First posted 20 Apr 2023cs.AI cs.LG cs.MAcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 16 of its 30 references that are in the map. First posted on arXiv 20 Apr 2023.

Builds on

16 of 30 references.

References · 16

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  4. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  5. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,103
  6. 2019Emergent Tool Use From Multi-Agent Autocurriculacited by 313
  7. 2018Human-level performance in first-person multiplayer games with population-based deep reinforcement learningcited by 264
  8. 2019Google Research Football: A Novel Reinforcement Learning Environmentcited by 260
  9. 2019Adversarial Policies: Attacking Deep Reinforcement Learningcited by 214
  10. 2019Mastering Complex Control in MOBA Games with Deep Reinforcement Learningcited by 161
  11. 2017Emergent Complexity via Multi-Agent Competitioncited by 120
  12. 2019Open-ended Learning in Symmetric Zero-sum Gamescited by 96
4 more
  1. 2019Keeping Your Distance: Solving Sparse Reward Tasks Using Self-Balancing Shaped Rewardscited by 78
  2. 2020Suphx: Mastering Mahjong with Deep Reinforcement Learningcited by 58
  3. 2020A Survey of Behavior Trees in Robotics and AIcited by 55
  4. 2019What Can Learned Intrinsic Rewards Capture?cited by 36

Built on by

Not cited yet.