Cohere to Host Lecture on Explaining RL with Shapley Values

Cohere_Labs · x · 2026-08-20

Cohere Labs Open Science Community will host a session on August 25th featuring Daniel Beechey. The talk, titled "Explaining Reinforcement Learning with Shapley Values: Theory and Algorithms," addresses how to explain RL agent behaviors, outcomes, and predictions using game-theoretic foundations. It will cover SVERL (ICML 2023) and FastSVERL (NeurIPS 2025), making Shapley-based explanations practical for deployed agents.

Original post →

More from Research

Research channel →