Research map / Learning theory and algorithms / Submodular and game algorithms
Hindsight and Sequential Rationality of Correlated Play
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use an action deviation that upgrades seating and then follows event recommendations | EFCE recommendations in extended battle-of-the-sexes · Extended battle-of-the-sexes | player one expected utility: +1.5 -> +2.5 | Helped |
| Use a causal or action deviation to play Tails/ at the Match information set | CFCE recommendations in extended matching pennies · Extended matching pennies | player one expected utility: 0 -> +1 | Helped |
| Use an external deviation that always plays Right | CFCE recommendations in MacQueen's counterexample · MacQueen's counterexample | player one expected utility: +1 -> +2 | Helped |
| Use causal or action deviations rather than only counterfactual deviations | CFR self-play in the extended Shapley's game · Extended Shapley's game | deviation regret | Mixed |
| Use counterfactual deviations rather than causal or action deviations | CFR self-play · Extensive-form games | regret | Helped |
| Use no-internal-regret learners instead of the usual no-external-regret learners | CFR · Extensive-form games | informed counterfactual deviation regret | Helped |
| Weight counterfactual values by the player's reach probability | CFR-like algorithm · Extensive-form games | action deviation regret | Helped |
Closest papers by meaning
- Efficient Deviation Types and Learning for Hindsight Rationality in Extensive-Form Games (ICML 2021 · similarity 0.93)
- Mediator Interpretation and Faster Learning Algorithms for Linear Correlated Equilibria in General Sequential Games (ICLR 2024 · similarity 0.90)
- Convergence of No-Swap-Regret Dynamics in Self-Play (NeurIPS 2024 · similarity 0.90)
- The impact of uncertainty on regularized learning in games (ICML 2025 · similarity 0.90)
- Memory Asymmetry Creates Heteroclinic Orbits to Nash Equilibrium in Learning in Zero-Sum Games (AAAI 2024 · similarity 0.89)
- Optimism Without Regularization: Constant Regret in Zero-Sum Games (NeurIPS 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.