MILO: Automated Harness Discovery via Orchestrated Multi-Agent Evolution
Paper • 2609.38349 • Published • 19
AI & ML interests
Deep Reinforcement Learning; Robotics
Recent Activity
View all activity
Zhehui-Huang
authored 2
papers 4 days ago
Zhehui-Huang
authored a
paper about 1 year ago
Zhehui-Huang
authored a
paper about 2 years ago
Zhehui-Huang
authored 7
papers over 2 years ago
From Words to Routes: Applying Large Language Models to Vehicle Routing
Paper • 2403.10795 • Published
HyperPPO: A scalable method for finding small policies for robotic control
Paper • 2309.16663 • Published
Decentralized Control of Quadrotor Swarms with End-to-end Deep Reinforcement Learning
Paper • 2109.07735 • Published • 1
Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning
Paper • 2006.11751 • Published
QuadSwarm: A Modular Multi-Quadrotor Simulator for Deep Reinforcement Learning with Direct Thrust Control
Paper • 2306.09537 • Published
Collision Avoidance and Navigation for a Quadrotor Swarm Using End-to-end Deep Reinforcement Learning
Paper • 2309.13285 • Published
Guaranteed Trust Region Optimization via Two-Phase KL Penalization
Paper • 2312.05405 • Published