12/27/2022 0 Comments Stockfish chess make ai fasterThis paper explores several key questions in the context of chess play: In reinforcement learning situtuations though, the model is trained by getting feedback on the outcome of its interactions with an external enviroment: in the case of AlphaZero, the training is done by playing games against itself. The second point in particular is quite important – if you train a model by giving it a set of labelled data based on what a human did in a given situation, then you’ll get a model that mimics what humans do. we have a recognised method of assessing player skill levels (rating points).we also have large databases of human games available though,. these engines were not trained on human games.we have chess engines that have achieved super-human performance (e.g, AlphaZero).These are big questions, and chess turns out to be the perfect testbed for exploring them: I.e., how do human and AI performances compare at different skill levels, and are the learning trajectories similar? This is the question that most interests me in the paper, because if we can successfully model human learning trajectories on a task, then we ought to be able to build very effective AI coaches to improve human performance. The central challenge in realizing these opportunities is that algorithms approach problems very differently from the ways that people do, and thus may be uninterpretable, hard to learn from, or even dangerous for humans to follow.Īs well as outright behaviour and performance once fully trained, a related interesting question is whether or not the AI model improves with training in the same way that humans do on the same task as their skill levels increase. ‘ Ten challenges for making automation a ‘team player’ in joint human-agent activity‘). Human-machine collaboration offers a lot of potential to enhance and augment human performance, but this requires the human and the machine to be ‘on the same page’ to be truly effective (see e.g. make the case that this difference in approaches really does matter. But where humans are still involved in task performance, supervision, or evaluation, then McIlroy-Young et al. How human-like is superhuman AI?ĪI models can learn to perform some tasks to human or even super-human levels, but do they then perform those tasks in a human-like way? And does that even matter so long as the outcomes are good? If we’re going to hand everything over to AI and get out of the way, then maybe not. It’s been a while, but it’s time to start reading CS papers again! We’ll ease back into it with one or two papers a week for a few weeks, building back up to something like 3 papers a week at steady state. Aligning superhuman AI with human behavior: chess as a model system, McIlroy-Young et al., KDD’20
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |