Science, Space and Technology News 2024
Researchers at MIT and the University of Washington have developed a new method for modeling the decision-making behaviors of agents, taking into account computational constraints. This model, which can predict future actions from past behavior, aims to improve AI systems’ collaboration with humans by understanding and adapting to human irrationalities and decision-making processes. Credit: SciTechDaily.
This irrationality, which is especially difficult to model, often boils down to computational constraints. A human can’t spend decades thinking about the ideal solution to a single problem.developed a way to model the behavior of an agent, whether human or machine, that accounts for the unknown computational constraints that may hamper the agent’s problem-solving abilities.
“If we know that a human is about to make a mistake, having seen how they have behaved before, the AI agent could step in and offer a better way to do it. Or the agent could adapt to the weaknesses that its human collaborators have. Being able to model human behavior is an important step toward building an AI agent that can actually help that human,” he says.
To build their model, Jacob and his collaborators drew inspiration from prior studies of chess players. They noticed that players took less time to think before acting when making simple moves and that stronger players tended to spend more time planning than weaker ones in challenging matches. The first step in their method involves running an algorithm for a set amount of time to solve the problem being studied. For instance, if they are studying a chess match, they might let the chess-playing algorithm run for a certain number of steps. At the end, the researchers can see the decisions the algorithm made at each step.
“For me, the most striking thing was the fact that this inference budget is very interpretable. It is saying tougher problems require more planning or being a strong player means planning for longer. When we first set out to do this, we didn’t think that our algorithm would be able to pick up on those behaviors naturally,” Jacob says.
United Kingdom Latest News, United Kingdom Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
New deep learning model predicts water and energy demands in agriculture with great accuracyWater scarcity and the high cost of energy represent the main problems for irrigation communities, which manage water for this end, making it available to agriculture.
Read more »
New CRC Risk Prediction Model Outperforms Polyp-Based ModelA comprehensive model that includes additional risk factors beyond previous polyp findings showed improved post-colonoscopy risk stratification for colorectal cancer.
Read more »
Tesla Model Y & Model 3 Cost $10,000 Less Than Average New Car PriceClean Tech News & Views: EVs, Solar Energy, Batteries
Read more »
AI deep learning accelerates brain-computer interface (BCI) neurotech accuracy.AI deep learning model predicts behavior at nearly real-time speed with 95% accuracy.
Read more »
Dozens Of Tesla Model 3s And Model Ys Just Landed In Chile.Chile has the world's largest lithium deposits, but its EV market isn't anything to brag about. With Tesla's entry, things should spice up.
Read more »
Tesla Model 3 vs. Model S: Different in Size, But What Else?Tesla’s two cars differ in size and price, but what other features distinguish these electric sedans?
Read more »