Curious Pong: Two novelty-seeking agents, forced to play Pong against one another, create increasingly extreme rallies.Montezuma’s Revenge: By 2015 a reinforcement learner can play 60 different Atari games - the majority impossibly well - but can’t score a single point on one game humans find tediously simple.
The Danish Bicycle: A reinforcement learning agent figures out that it can better achieve its goal by riding in circles as quickly as possible than reaching its purported destination. Tree Senility: Agents become so good at living in trees to escape predators that they forget how to leave, starve, and die. Pitts & McCulloch: A homeless teenager and his foster father figure invent the idea of the neural net. Couch Potato: An agent trained to be curious is stopped in its quest to navigate a maze by a paralysing TV screen. 
ALVINN: A student teaches a military vehicle to drive between Pittsburgh and Lake Erie, without intervention, in the early nineties, using a computer with a tenth the processing capacity of an Apple Watch. The Riddle of Dopamine: The development of reinforcement learning solves a long-standing mystery of how humans are able to learn from their experience. Here’s a tease of 10 Hollywood-worthy stories from the episode: Listeners loved our episode about his book Algorithms to Live By - so when the team read his new book, The Alignment Problem, and found it to be an insightful and comprehensive review of the state of the research into making advanced AI useful and reliably safe, getting him back on the show was a no-brainer.īrian has so much of substance to say this episode will likely be of interest to people who know a lot about AI as well as those who know a little, and of interest to people who are nervous about where AI is going as well as those who aren’t nervous at all. Call me when AI can tell me what the word ‘it’ means in such and such a sentence.” And then it’s like, “Okay, well we’re there, so, can we call you now?”īrian Christian is a bestselling author with a particular knack for accurately communicating difficult or technical ideas from both mathematics and computer science. 
It’s funny, if you track a lot of the nay-saying that existed circa 2017 or 2018 around AGI, a lot of people would be like, “Well, call me when AI can do that.
0 kommentar(er)
