A new paper discusses adopting a humanlike playstyle.
Have a look at a paper that describes an AI agent that was trained to play the bestselling first-person-shooter multiplayer game called Counter-Strike; Global Offensive from pixel input. The agent, a deep neural network, uses the performance of the medium difficulty built-in AI on the deathmatch game mode, plus learns a humanlike playstyle. 'Unlike much prior work in games, no API is available for CSGO, so algorithms must train and run in real-time," noted the team.
"This limits the quantity of on-policy data that can be generated, precluding many reinforcement learning algorithms. Our solution uses behavioural cloning - training on a large noisy dataset scraped from human play on online servers (4 million frames, comparable in size to ImageNet), and a smaller dataset of high-quality expert demonstrations." The research team states that this scale is "an order of magnitude larger than prior work on imitation learning in FPS games."
You can find the paper here. Don't forget to join our new Telegram channel, our Discord, follow us on Instagram and Twitter, where we are sharing breakdowns, the latest news, awesome artworks, and more.