Reinforcement learning is one of the exciting branches of artificial intelligence. It plays an important role in game-playing AI systems, modern robots, chip-design systems, and other applications.

Why reinforcement learning plateaus without representation depth (and other key takeaways from NeurIPS 2025) ...

“We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1. DeepSeek-R1-Zero, a model trained via large-scale reinforcement learning (RL) without supervised fine-tuning (SFT ...

MIT's mini cheetah robot has broken its own personal best (PB) speed, hitting 8.72 mph (14.04 km/h) thanks to a new model-free reinforcement learning system that allows the robot to figure out on its ...

Humans possess a remarkable balance between stability and flexibility, enabling them to quickly establish new plans and adjust goals even in the face of sudden changes. However, "model-free ...

This study seeks to construct a basic reinforcement learning-based AI-macroeconomic simulator. We use a deep RL (DRL) approach (DDPG) in an RBC macroeconomic model. We set up two learning scenarios, ...

Researchers from Fudan University and Shanghai AI Laboratory have conducted an in-depth analysis of OpenAI’s o1 and o3 models, shedding light on their advanced reasoning capabilities. These models, ...

Reinforcement learning is a subfield of machine learning concerned with how an intelligent agent can learn through trial and error to make optimal decisions in its ...