IEEE

Uncertainty-Aware Model-Based Multi-Agent Deep Reinforcement Learning for Robust Active Voltage Control

Abstract: The large-scale injection of new energy systems into active distribution networks (ADNs) has caused voltage violations, challenging the stable operation of power grids. Recently, deep ...
IEEE

Multi-Agent Hierarchical Deep Reinforcement Learning for HVAC Control With Flexible DERs

Abstract: As electricity consumption in commercial and residential buildings continues to rise, reducing energy costs presents an increasing challenge. Heating, ventilating, and air-conditioning (HVAC ...
VentureBeat

Meta’s DreamGym framework trains AI agents in a simulated world to cut reinforcement learning costs

Researchers at Meta, the University of Chicago, and UC Berkeley have developed a new framework that addresses the high costs, infrastructure complexity, and unreliable feedback associated with using ...
InfoWorld

How multi-agent collaboration is redefining real-world problem solving

When I first started working with multi-agent collaboration (MAC) systems, they felt like something out of science fiction. It’s a group of autonomous digital entities that negotiate, share context, ...
Seeking Alpha

CoreWeave unveils serverless reinforcement learning capability to build AI agents; stock rises

CoreWeave (NASDAQ:CRWV) announced the launch of Serverless RL, a fast way to train AI agents using reinforcement learning, or RL. Shares of the company surged about 9% on Wednesday. The company said ...
Frontiers

Deep Reinforcement Learning for complex hydropower management: evaluating Soft Actor-Critic with a learned system dynamics model

Introduction: Optimizing the operation of interconnected hydropower systems presents significant challenges due to complex non-linear dynamics, hydrological uncertainty, and the need to balance ...
Forbes

How To Design AI Agent Context: 3 Keys To Multi-Agent Success

Forbes contributors publish independent expert analyses and insights. Anne T. Griffin is an AI product leader and educator. What agent swarms (a team of agents) and human teams have in common is that ...
GitHub

DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL

We evaluate DeepDive not only on challenging search tasks (e.g., BrowseComp, BrowseComp-ZH) but also on simpler benchmarks such as HotpotQA, Frames, and WebWalker. DeepDive-32B (SFT and RL) ...
GitHub

DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL

Overview DeepDive presents an automated approach for training deep search agents that can navigate complex, multi-step information-seeking tasks. Our method combines automated data synthesis from ...
Scientific Research Publishing

Finistrella, S., Mariani, S. and Zambonelli, F. (2025) Multi-Agent Reinforcement Learning for Cybersecurity: Classification and Survey.

ABSTRACT: The balance between individuals’ interest in protecting their private information and the interests of other entities (other individuals, confidants, Internet companies, corporations, and ...