An attractive asteroid game was described in the paper from 2007:
quote: “In our first experiment, the virtual agent is a spaceship pilot, The pilot’s task is to maneuver the spaceship through random asteroid fields” Jonathan Dinerstein: "Learning Policies for Embodied Virtual Agents through Demonstration", 2007 (page 4)
In theory, this game can be solved with Reinforcement learning, or to be more specific with a support vector machine (SVM) and epsilon-regression scheme with a Gaussian kernel. But it seems, that this task is harder than it looks like:
quote: “Although many powerful AI and machine learning techniques exist, it remains difficult to quickly create AI for embodied virtual agents. [...] it is quite challenging to achieve natural-looking behavior since these aesthetic goals must be integrated into the fitness function” (page 1-2)
I really want to understand how reinforcement learning works. I built a simple game to test this. There are squares falling from the sky and you have the arrow keys to escape.
- Player life
- Survival time
- Maximum survival time