An easier way to calibrate.
From MaRDI portal
Publication:1818288
DOI10.1006/game.1999.0726zbMath1131.91310MaRDI QIDQ1818288
David K. Levine, Drew Fudenberg
Publication date: 4 January 2000
Published in: Games and Economic Behavior (Search for Journal in Brave)
Full work available at URL: http://nrs.harvard.edu/urn-3:HUL.InstRepos:3203773
91A35: Decision theory for games
Related Items
Good Randomized Sequential Probability Forecasting is Always Possible, Testing theories with learnable and predictive representations, Regret minimization in repeated matrix games with variable stage duration, A nonmanipulable test, Calibrated learning and correlated equilibrium, Learning, hypothesis testing, and Nash equilibrium., Regret in the on-line decision problem, A proof of calibration via Blackwell's approachability theorem., Conditional universal consistency., Calibrated forecasting and merging, Mostly calibrated, Online calibrated forecasts: memory efficiency versus universality for learning in games, Approachability, regret and calibration: implications and equivalences, Deterministic calibration and Nash equilibrium, Merging and testing opinions
Cites Work
- Consistency and cautious fictitious play
- An analog of the minimax theorem for vector payoffs
- A proof of calibration via Blackwell's approachability theorem.
- Calibrated forecasting and merging
- Self-Calibrating Priors Do Not Exist
- Merging of Opinions with Increasing Information
- The Well-Calibrated Bayesian
- Unnamed Item
- Unnamed Item