Talk explains RL with Shapley values
Daniel Beechey presents theory and algorithms for explaining reinforcement learning agents using Shapley values, addressing the trust gap in superhuman decision-making systems.
Featured · Daniel Beechey
1 source
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- SentinelOne CEO discusses earnings and AI's cybersecurity impact
- Andrew Ng: Biggest AI opportunities aren't where you think
- OpenAI co-founder warns of closing window to secure internet
- Yann LeCun: Provably safe AI is impossible
- Gemini 3.8 Flash preview reportedly in use at Google