CARA 2.0: One Engineer Built a Better Robot Dog
An independent robotics engineer unveils CARA 2.0, an open-source quadruped robot dog that rivals commercial offerings a…
🏷️ Reinforcement Learning
29 articles about 'Reinforcement Learning'
CMU Unveils RL Framework for Robotic Manipulation
Carnegie Mellon researchers introduce a reinforcement learning framework that enables robots to learn complex manipulati…
Berkeley AI Lab Releases Open Source RLHF Framework
UC Berkeley's AI research lab publishes a comprehensive open source framework for RLHF training of large language models…
MIT CSAIL Unveils RL Breakthrough for Robot Dexterity
MIT CSAIL researchers introduce a novel reinforcement learning framework that dramatically improves robotic manipulation…
UC Berkeley AI Agent Masters Robotic Surgery Tasks
UC Berkeley researchers develop a reinforcement learning agent capable of performing complex robotic surgery tasks with …
Toyota AI Masters Autonomous Drifting Stunts
Toyota Research Institute unveils an AI system that enables autonomous vehicles to perform precision drifting maneuvers,…
Grab Singapore Cuts Delivery Times 25% With AI Routes
Grab deploys AI-powered route optimization across Singapore, reducing delivery times by 25% and reshaping Southeast Asia…
AlphaProof Wins Silver at Math Olympiad
Google DeepMind's AlphaProof system scores 28 out of 42 points at the 2024 International Mathematical Olympiad, narrowly…
CMU Builds Self-Improving AI Code Generator via RL
Carnegie Mellon researchers develop a reinforcement learning framework that lets code generation models iteratively impr…
UC Berkeley Unveils RL Framework for Robotic Manipulation
UC Berkeley researchers introduce a reinforcement learning framework that dramatically improves robotic manipulation tas…
New Drone Search-and-Rescue Framework: Rule-Guided Reinforcement Learning Breaks Through Training Bottlenecks
A new paper proposes a hierarchical decision-making framework that combines a fixed rule-based high-level advisor with a…
Tactile and Proximity Sensors Power New Collision Avoidance Research for Humanoid Robots
A new study proposes a reinforcement learning framework based on egocentric tactile and proximity sensors for whole-body…