Goto

Collaborating Authors

Agents


Why do policy gradient methods work so well in cooperative MARL? Evidence from policy representation

AIHub

In cooperative multi-agent reinforcement learning (MARL), due to its on-policy nature, policy gradient (PG) methods are typically believed to be less sample efficient than value decomposition (VD) methods, which are off-policy. However, some recent empirical studies demonstrate that with proper input representation and hyper-parameter tuning, multi-agent PG can achieve surprisingly strong performance compared to off-policy VD methods. Why could PG methods work so well? In this post, we will present concrete analysis to show that in certain scenarios, e.g., environments with a highly multi-modal reward landscape, VD can be problematic and lead to undesired outcomes. In addition, PG methods with auto-regressive (AR) policies can learn multi-modal policies.


Meet ML@GT: Lara J. Martin Trains AI Agents to Become Storytellers

#artificialintelligence

The Machine Learning Center at Georgia Tech (ML@GT) is home to many talented students from across campus, representing all six of Georgia Tech's colleges and the Georgia Tech Research Institute (GTRI). These students have diverse backgrounds and a wide variety of interests both inside and outside of the classroom. Today, we'd like you to meet Lara Martin, a fifth-year Ph.D. student who is interested in teaching artificial intelligence agents to tell interesting and coherent stories. Tell us about your research interests. Where might people be impacted them in everyday life?


Decomposing your complex AI problem: Hierarchy

#artificialintelligence

Problem worlds often come with an innate hierarchy. Naturally, this may prompt the question: which level(s) of the hierarchy should be modelled? For example, the US Stock Market can be modelled as a whole or at the index level -- think, the Dow Jones, or for individual stocks. In a linear system, the way that the lower levels interact with the upper levels is "linear" or directly correlated. Take the example of an analytics system for business intelligence and reporting -- sales, inventories, etc.


New Advancements in the field of Swarm Robotics part2(IOT + Computer Vision)

#artificialintelligence

Abstract: With the rapid development of AI and robotics, transporting a large swarm of networked robots has foreseeable applications in the near future. Existing research in swarm robotics has mainly followed a bottom-up philosophy with predefined local coordination and control rules. However, it is arduous to verify the global requirements and analyze their performance. This motivates us to pursue a top-down approach, and develop a provable control strategy for deploying a robotic swarm to achieve a desired global configuration. Specifically, we use mean-field partial differential equations (PDEs) to model the swarm and control its mean-field density (i.e., probability density) over a bounded spatial domain using mean-field feedback.


Meet the A3 Artificial Intelligence Tech Strategy Board Members

#artificialintelligence

In the first of our series of A3 interviews with AI leaders, John Lizzi, the Executive Leader - Robotics and Autonomous Systems at GE, discusses how to develop AI projects that focus on business objectives. Lizzi, who serves as the chair of the Association for Advancing Automation's Artificial Intelligence Technology Strategy Board, says that AI is enabling intelligent systems to operate in the complex and uncertain world. Check out his advice on how to craft your AI strategy. How would you advise companies to choose their artificial intelligence projects – and what questions do they need to answer before they begin? Win hearts and minds: I think it's important to note that injecting new and disruptive technology into a business is hard no matter what technology you're talking about.


Cybersecurity mesh provides decentralized safety and swarm AI for remote-first enterprises - Channel969

#artificialintelligence

Be a part of executives from July 26-28 for Remodel's AI & Edge Week. Hear from high leaders talk about matters surrounding AL/ML know-how, conversational AI, IVA, NLP, Edge, and extra. Cybersecurity mesh has been named a high strategic know-how development for 2022 by Gartner. In line with Gartner's report, cybersecurity mesh is a cutting-edge conceptual safety structure methodology that permits right this moment's scattered enterprises to increase and implement safety the place it's most wanted. David Carvalho, CEO and founding father of cybersecurity community Naoris Protocol, instructed VentureBeat through e-mail that cybersecurity mesh is a versatile, composable structure that integrates broadly distributed safety companies.


Using AI to train teams of robots to work together

#artificialintelligence

"It's easier when agents can talk to each other," said Huy Tran, an aerospace engineer at Illinois. "But we wanted to do this in a way that's decentralized, meaning that they don't talk to each other. We also focused on situations where it's not obvious what the different roles or jobs for the agents should be." Tran said this scenario is much more complex and a harder problem because it's not clear what one agent should do versus another agent. "The interesting question is how do we learn to accomplish a task together over time," Tran said.


AI-based MARL method improves cooperation between teams of robots - Dataconomy

#artificialintelligence

Researchers from the University of Illinois at Urbana-Champaign began with this more challenging task. They created a technique using multi-agent reinforcement learning (MARL), a form of artificial intelligence, to teach many agents to cooperate. Individual agents, such as robots or drones, can cooperate and finish a task when communication channels are open. What happens, though, if their technology is insufficient or the signals are jammed, making communication impossible? There are lots of research going on to improve the efficiency of artificial intelligence systems, lately, it is found that the selective regression method improves AI accuracy.


RT/ Using AI to train teams of robots to work together

#artificialintelligence

The global market for robots is expected to grow at a compound annual growth rate (CAGR) of around 26 percent to reach just under 210 billion U.S. dollars by 2025. When communication lines are open, individual agents such as robots or drones can work together to collaborate and complete a task. But what if they aren't equipped with the right hardware or the signals are blocked, making communication impossible? University of Illinois Urbana-Champaign researchers started with this more difficult challenge. They developed a method to train multiple agents to work together using multi-agent reinforcement learning, a type of artificial intelligence.


Bonsai Brain - A low code platform to build AI agents

#artificialintelligence

Bonsai Brain is one of the ongoing projects of Microsoft, which aims to develop a low code AI-based component that is integrated with Automation systems. The Bonsai brain is simulated and trained in a manner to handle situations and to be fault tolerant even during unexpected or unseen circumstances. Bonsai's brain focuses on adding value to various autonomous systems, processes, and equipment but also focuses on growing customer trust by ensuring continuous operations. In this article, let us try to understand the Bonsai Brain with respect to this context. Bonsai Brain is an ongoing research project of Microsoft that focuses on simulating and developing a low code-based AI component that can be used for various Autonomous tasks and applications.