AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
How Do You Inform Your Model of Your Preferences?
We draw inspiration from the actual domain of racing, right? So so much students have no vea racing rules. We have watched interviews of every crash that has happened and how the drivers explain what went wrong in theit crash. There could be a cast ofa you don't want to be a certain distance laterally from any opponent. Tan thats o gives the trajectory a certain weight. Another one is some smoothness property, so that the car will spin out if you yank the steering wheel because they are very sensitive vehical dynamics. This is the layer where we can sprinkle in the objective functions for collision avoidance,. For multi agent racing, for taking the sticking as close as possible to