Guided Flow Policy: Learning from High-Value Actions in Offline Reinforcement Learning
Paper
• 2512.03973 • Published
Theotime Le Hellard
TheotimeLH
·
AI & ML interests
Robotics, Simulation, Reinforcement Learning, Diffusion, Flow Matching
Recent Activity
authored
a paper
about 11 hours ago
Guided Flow Policy: Learning from High-Value Actions in Offline Reinforcement Learning Organizations
authored a paper about 11 hours ago