Towards Playing Full MOBA Games with Deep Reinforcement Learning

11/25/2020
by   Deheng Ye, et al.
5

MOBA games, e.g., Honor of Kings, League of Legends, and Dota 2, pose grand challenges to AI systems such as multi-agent, enormous state-action space, complex action control, etc. Developing AI for playing MOBA games has raised much attention accordingly. However, existing work falls short in handling the raw game complexity caused by the explosion of agent combinations, i.e., lineups, when expanding the hero pool in case that OpenAI's Dota AI limits the play to a pool of only 17 heroes. As a result, full MOBA games without restrictions are far from being mastered by any existing AI system. In this paper, we propose a MOBA AI learning paradigm that methodologically enables playing full MOBA games with deep reinforcement learning. Specifically, we develop a combination of novel and existing learning techniques, including curriculum self-play learning, policy distillation, off-policy adaption, multi-head value estimation, and Monte-Carlo tree-search, in training and playing a large pool of heroes, meanwhile addressing the scalability issue skillfully. Tested on Honor of Kings, a popular MOBA game, we show how to build superhuman AI agents that can defeat top esports players. The superiority of our AI is demonstrated by the first large-scale performance test of MOBA AI agent in the literature.

READ FULL TEXT

page 4

page 13

research
12/13/2019

Dota 2 with Large Scale Deep Reinforcement Learning

On April 13th, 2019, OpenAI Five became the first AI system to defeat th...
research
12/27/2022

Teamwork under extreme uncertainty: AI for Pokemon ranks 33rd in the world

The highest grossing media franchise of all times, with over $90 billion...
research
05/25/2023

Lucy-SKG: Learning to Play Rocket League Efficiently Using Deep Reinforcement Learning

A successful tactic that is followed by the scientific community for adv...
research
08/02/2017

Helping AI to Play Hearthstone: AAIA'17 Data Mining Challenge

This paper summarizes the AAIA'17 Data Mining Challenge: Helping AI to P...
research
03/20/2022

Does DQN really learn? Exploring adversarial training schemes in Pong

In this work, we study two self-play training schemes, Chainer and Pool,...
research
01/27/2023

Policy-Value Alignment and Robustness in Search-based Multi-Agent Learning

Large-scale AI systems that combine search and learning have reached sup...
research
09/01/2020

AI solutions for drafting in Magic: the Gathering

Drafting in Magic: the Gathering is a sub-game of a larger trading card ...

Please sign up or login with your details

Forgot password? Click here to reset