SRI International, for example, as part of DARPA’s Lifelong-Learning Machines research program, is training AI systems to play the role-playing game StarCraft: Remastered in order to train them to take collective action and act in swarms or travel in group formations as characters do in the game.ĭeepMind has also found much value in StarCraft. Insights that can be drawn from multi-agent environments can be used to inform human-machine interaction and train AI systems to complement one another or work together. Last month, OpenAI revealed it used reinforcement learning to train AI to beat talented teams of humans playing Dota 2. Tagging, the act of touching an opponent to send them back to their spawning point, was incorporated into tactics used to win matches as well.ĭeepMind’s study is the latest from AI researchers to apply reinforcement learning to video games as a way to train a machine strategy, memory, or other traits common among humans but which do not naturally occur with computers. No rules of the game were given to machines beforehand, yet over time, FTW learned basic strategies like home base defense, following a teammate, or camping out in an opponent’s base to tag them after a flag has been captured.
The only signal used to teach the agents was whether their team won the game by capturing the most flags within five minutes. Agents also operated in slow or fast modes and developed their own internal rewards systems. Indoor environments with flat terrain and outdoor environments with varying elevations were also introduced.
The research was carried out with some unique challenges.Ĭapture the Flag was played in settings with random map layouts rather than a static, consistent environment in order to train systems’ general understanding for better outcomes. Interestingly enough, a survey of human participants found FTW to be more collaborative than human teammates.Īuthors of the study include DeepMind founder and CEO Demis Hassabis. FTW continued to keep its edge over human players even when its tagging abilities were suppressed to levels comparable to humans. On average, human-machine teams captured 16 flags per game less than a team of two FTW agents.Īgents were found to be efficient than humans in tagging, achieving the tactic 80 percent of the time compared to humans 48 percent. In a tournament with and against 40 human Capture the Flag players, machine-only teams went undefeated in games against human-only teams and stood a 95 percent chance of winning against teams in which humans played with a machine partner.
Whereas some previous studies of video game play with reinforcement learning focus on environments with a handful of players, DeepMind’s experiment involved 30 agents playing concurrently four at a time against humans or machines.
Three top investment pros open up about what it takes to get your video game funded.
0 kommentar(er)
