Deep Reinforcement Learning researches in RTS and MOBA games (Around 2020)

Source: Team Liquid Website
Source: deepmind.com
Source: Grandmaster level in StarCraft II using multi-agent reinforcement learning
Source: Grandmaster level in StarCraft II using multi-agent reinforcement learning
Source: Grandmaster level in StarCraft II using multi-agent reinforcement learning
Source: Grandmaster level in StarCraft II using multi-agent reinforcement learning
  1. Main agent: The one to be deployed
  2. League Exploiter: To find common weaknesses from past iterations in the League
  3. Main Exploiter: To find common weakness of the current main agent
Win rate and EPM collected by Race
Source: Grandmaster level in StarCraft II using multi-agent reinforcement learning
Source: Mastering Complex Control in MOBA Games with Deep Reinforcement Learning
Source: Mastering Complex Control in MOBA Games with Deep Reinforcement Learning
  1. The AI Server with game environments: A cluster of servers with game environments, agents, and gain information with softmax
  2. Dispatch module: Gather information such as penalty, feature values, etc. and pack the gathered information before sending it to the memory pool
  3. Memory Pool: A server running a memory efficient circular queue.
  4. Reinforcement Learner: A distributed training environment that pulls information from the memory pool and does RL training. Information is shared through RAM to achieve faster transmission. The updated weights and award/penalty are sent directly back to the AI server.
Source: Mastering Complex Control in MOBA Games with Deep Reinforcement Learning
Source: Mastering Complex Control in MOBA Games with Deep Reinforcement Learning

--

--

--

Aspiring computer scientist

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Web design and AI: still a long way to go

Exploration Of Challanges And Opportunities Of AI In Technology

There is one more name for that loop

Redefining Intelligence In The Age Of AI

Update: yAI.Finance Tech Progress 18th Nov, 2020

A closer look at the Turing Test (Part 4)

Scientists at MIT have Discovered a New Antibiotic Using Artificial Intelligence

Neon Genesis | The Juice

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Junyang Jin

Junyang Jin

Aspiring computer scientist

More from Medium

[NeurIPS 2018] Diversity-Driven Exploration Strategy for Deep Reinforcement Learning

REINFORCE — Empower something that has potential.

Treasure Maze Reinforced Learning