Conditional universal consistency.
From MaRDI portal
Publication:1818287
DOI10.1006/game.1998.0705zbMath1131.91309OpenAlexW2013478841MaRDI QIDQ1818287
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:3204826
Related Items (39)
Replicator dynamics: old and new ⋮ A general internal regret-free strategy ⋮ Belief-based equilibrium ⋮ Exploitable actions of believers in the ``law of small numbers in repeated constant-sum games ⋮ Learning correlated equilibria in games with compact sets of strategies ⋮ AWESOME: a general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents ⋮ Learning in perturbed asymmetric games ⋮ Approachability with bounded memory ⋮ Dynamic benchmark targeting ⋮ Regret matching with finite memory ⋮ Constrained no-regret learning ⋮ Approachability with delayed information ⋮ No-regret algorithms in on-line learning, games and convex optimization ⋮ Recency, consistent learning, and Nash equilibrium ⋮ Learning, hypothesis testing, and Nash equilibrium. ⋮ Approachability, regret and calibration: implications and equivalences ⋮ Regret-based continuous-time dynamics. ⋮ Supermartingales in Prediction with Expert Advice ⋮ Regret minimization in repeated matrix games with variable stage duration ⋮ Learning purified mixed equilibria ⋮ Learning in Games ⋮ Unnamed Item ⋮ A continuous-time approach to online optimization ⋮ Exponential weight algorithm in continuous time ⋮ Bounding the inefficiency of outcomes in generalized second price auctions ⋮ Note on universal conditional consistency ⋮ A general class of adaptive strategies ⋮ EFFICIENT TESTING OF FORECASTS ⋮ Internal regret in on-line portfolio selection ⋮ Internal regret in on-line portfolio selection ⋮ A wide range no-regret theorem ⋮ Transferable deposits as a screening mechanism ⋮ Regret in the on-line decision problem ⋮ Calibrated forecasting and merging ⋮ Calibration and Internal No-Regret with Random Signals ⋮ On the empirical relevance of correlated equilibrium ⋮ Learning in nonatomic games. I: Finite action spaces and population games ⋮ Correlated equilibria in homogeneous good Bertrand competition ⋮ A unifying learning framework for building artificial game-playing agents
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Consistency and cautious fictitious play
- On repeated games with incomplete information played by non-Bayesian players
- Learning mixed equilibria
- Three problems in learning mixed-strategy Nash equilibria
- The weighted majority algorithm
- Learning to learn, pattern recognition, and Nash equilibrium
- Calibrated learning and correlated equilibrium
- Regret in the on-line decision problem
- Mixed equilibria and dynamical systems arising from fictitious play in perturbed games
- An easier way to calibrate.
- Calibrated forecasting and merging
- Evolution of beliefs and the Nash equilibrium of normal form games
- Self-Calibrating Priors Do Not Exist
- The Well-Calibrated Bayesian
- Universal prediction of individual sequences
- Self-Confirming Equilibrium
- On Pseudo-Games
This page was built for publication: Conditional universal consistency.
