"Exploration is Harder than Prediction: Cryptographically Separating ..."

Noah Golowich, Ankur Moitra, Dhruv Rohatgi (2024)

> Home

Details and statistics

DOI: 10.1109/FOCS61266.2024.00117

access: closed

type: Conference or Workshop Paper

metadata version: 2024-12-09

- view
  - electronic edition via DOI
  - unpaywalled version
  authority control:
- export record
  dblp key:
  - conf/focs/GolowichMR24
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/conf/focs/GolowichMR24
Noah Golowich, Ankur Moitra, Dhruv Rohatgi:
Exploration is Harder than Prediction: Cryptographically Separating Reinforcement Learning from Supervised Learning. FOCS 2024: 1953-1967

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.