When it comes to the early days of the FPS genre, there's really no substitute for the original trilogy of Quake games. These response-delayed agents still outperformed human participants, with strong humans only winning 21% of the time.By clicking 'enter', you agree to GameSpot's In a further study, we trained agents which have an inbuilt delay of a quarter of a second (267 ms) – that is, agents have a 267ms lag before observing the world – comparable with reported reaction times of human video game players. However, by artificially reducing this accuracy and reaction time, we saw that this was only one factor in their success. Thus, our agents’ superior performance might be a result of their faster visual processing and motor control.
Here’s an example of a reaction time test you can try yourself. Humans are comparatively slow to process and act on sensory input, due to our slower biological signalling. How did our agents perform as well as they did? First, we noticed that the agents had very fast reaction times and were very accurate taggers, which might explain their performance (tagging is a tactical action that sends opponents back to their starting point). This complexity makes first-person multiplayer games a fruitful and active area of research within the AI community.
The challenge for our agents is to learn directly from raw pixels to produce actions. These games represent the most popular genre of video game, and have captured the imagination of millions of gamers because of their immersive game play, as well as the challenges they pose in terms of strategy, tactics, hand-eye coordination, and team play. To investigate this problem, we look at 3D first-person multiplayer video games. This is an immensely difficult problem - because with co-adapting agents the world is constantly changing.
This is a setting we call multi-agent learning: many individual agents must act independently, yet learn to interact and cooperate with other agents. Billions of people inhabit the planet, each with their own individual goals and actions, but still capable of coming together through teams, organisations and societies in impressive displays of collective intelligence.
0 kommentar(er)
