MilitaryNews.com

Reinforcement learning is making a buzz in space

A (NRL) research team successfully conducted the first reinforcement learning (RL) control of a free-flyer in space on May 27 ...

Hong Yichang Applies for Deep Reinforcement Learning Patent, Empowering Robots' Autonomous Decision-Making Capabilities for Complex Tasks

In August 2025, Shanghai Hong Yichang Industrial Co., Ltd. applied for a patent titled "Robot Decision-Making Method Based on Deep Reinforcement Learning." This move indicates that deep reinforcement ...
The Conversation

What is reinforcement learning? An AI researcher explains a key method of teaching machines – and how it relates to training your dog

Ambuj Tewari receives funding from NSF and NIH. Understanding intelligence and creating intelligent machines are grand scientific challenges of our times. The ability to learn from experience is a ...

Tencent’s new AI technique teaches language models ‘parallel thinking’

The Parallel-R1 framework uses reinforcement learning to teach models how to explore multiple reasoning paths at once, ...

2025 AI Training New Discovery: Reinforcement Learning is More Effective than Rote Memorization

2025 AI Training New Discovery: Reinforcement Learning is More Effective than Rote Memorization ...
The Information

Everyone Wants To Be a Reinforcement Learning Startup

These days, artificial intelligence developers, investors and founders are all obsessed with “reinforcement learning,” a ...
The Register on MSN

China's DeepSeek applying trial-and-error learning to its AI 'reasoning'

Model can also explain its answers, researchers find Chinese AI company DeepSeek has shown it can improve the reasoning of its LLM DeepSeek-R1 through trial-and-error based reinforcement learning, and ...
VentureBeat

DeepSeek-R1’s bold bet on reinforcement learning: How it outpaced OpenAI at 3% of the cost

Want smarter insights in your inbox? Sign up for our weekly newsletters to get only what matters to enterprise AI, data, and security leaders. Subscribe Now (Updated Monday, 1/27 8am) DeepSeek-R1’s ...