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.
More from Research
- 7 parameters that control every LLM response explained — blaizedsouza · 2026-08-20
- DeepLabCut Celebrates 9th Anniversary with 1.14M Installations — TrackingActions · 2026-08-20
- Opinion: Loss metric is a relic unfit for modern data scales — gerardsans · 2026-08-20
- Opinion: Broken scaling laws result from ignoring output fidelity — gerardsans · 2026-08-20
- Language understanding requires internal modeling of space-time, emerges earlier — RexDouglass · 2026-08-20
- Jaap Jumelet Wins 2025 EurAI Dissertation Award for LLM Structure Research — banazir · 2026-08-20