In other words, a reward function is the guidance system that keeps a reinforcement-learning-powered agent locked on target. Ideally, these policies will result in the agent reaching some desirable end state (like “win at Go”), without a programmer or engineer having to hand-code every step the agent needs to take along the way. With enough repetition - and if there’s anything that computers are better at than people, it’s repetition - the agent learns patterns of action, or policies, that maximize its reward function. As the agent operates in the environment, actions that increase the value of the reward function get reinforced. Then set it loose in an environment, which could be any real or virtual world. The details of successfully using reinforcement learning in a particular domain are complex, but the general idea is simple: Give a learning algorithm, or “agent,” a reward function, a mathematically defined signal to seek out and maximize.
#Wrong sound effect vine software#
Reinforcement learning is a big part of what helped Google’s AlphaGo software beat the world’s best human player at Go, an ancient and intuitive game long considered invulnerable to machine learning. In all of these cases, we are trying to figure out this really hard problem: How do you make a machine that can figure its own task out?” The Problem With Points We want vehicles that can navigate complicated environments and rescue robots that can explore a building and find people who need rescuing. In logistics, we want inventory to be moved around and manipulated. “At home, we want to automate cleaning up and organizing objects.
“Pick your favorite application area and I’ll give you an example,” said Darrell, co-director of the Berkeley Artificial Intelligence lab. Such agents may be trained on video games now, but the impact of developing meaningfully “curious” AI would transcend any novelty appeal. (“Nothing is really new in machine learning,” said Rein Houthooft, a research scientist at OpenAI, an independent artificial intelligence research organization.) Approaches to using intrinsic motivation in AI have taken inspiration from psychology and neurobiology - not to mention decades-old AI research itself, now newly relevant. But this carrot-and-stick approach to machine learning has its limits, and artificial intelligence researchers are starting to view intrinsic motivation as an important component of software agents that can learn efficiently and flexibly - that is, less like brittle machines and more like humans and animals.