New KL Divergence Analogs Improve Reinforcement Learning Control

Researchers have introduced new divergences that act as analogs to Kullback-Leibler (KL) divergence, addressing its limitations in reinforcement learning, particularly when distributions do not match or in low-noise scenarios. These novel divergences, based on Wasserstein and Kalman-Wasserstein geometries, remain finite even as distributions degenerate. The study demonstrates their effectiveness in KL-regularized optimal control for linear systems with Gaussian noise, showing they prevent singularity and improve performance in examples like the double integrator and cart-pole. AI

IMPACT Introduces mathematical tools that could improve the stability and performance of reinforcement learning agents in complex control tasks.

RANK_REASON This is a research paper detailing new mathematical divergences for use in reinforcement learning. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• Kalman-Wasserstein divergence
• Kullback-Leibler divergence
• reinforcement learning
• TU Berlin
• Viktor Stein
• Wasserstein divergence

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →