AINeutralarXiv – CS AI · 10h ago6/10
🧠
Quantile Geometry Regularization for Distributional Reinforcement Learning
Researchers propose RQIQN, a new reinforcement learning method that improves quantile-based distributional RL by addressing distorted distribution estimates through Wasserstein distributionally robust optimization. The approach adds a lightweight correction to quantile targets that prevents distributional collapse while maintaining computational efficiency, demonstrating superior performance on navigation and Atari benchmarks.