# Monte Carlo Continual Resolving for Online Strategy Computation in Imperfect Information Games

arXiv: https://arxiv.org/abs/1812.07351 · HTML: https://mlsanity.com/paper/1812.07351/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Dec 2018.

## Built on by (most cited first, 7 of 7)

- [Student of Games: A unified learning algorithm for both perfect and imperfect information games](https://mlsanity.com/paper/2112.03178/) (2021)
- [Solving Common-Payoff Games with Approximate Policy Iteration](https://mlsanity.com/paper/2101.04237/) (2021)
- [RL-CFR: Improving Action Abstraction for Imperfect Information Extensive-Form Games with Reinforcement Learning](https://mlsanity.com/paper/2403.04344/) (2024)
- [Search in Imperfect Information Games](https://mlsanity.com/paper/2111.05884/) (2021)
- [Beyond Outcome-Based Imperfect-Recall: Higher-Resolution Abstractions for Imperfect-Information Games](https://mlsanity.com/paper/2510.15094/) (2025)
- [HSVI-based Online Minimax Strategies for Partially Observable Stochastic Games with Neural Perception Mechanisms](https://mlsanity.com/paper/2404.10679/) (2024)
- [GPU-CFR: 80x Faster Counterfactual Regret Minimization by Compiling the Game to Static Dataflow and CUDA Graph Replay](https://mlsanity.com/paper/2609.11923/) (2026)

## Abstract (arXiv)

Online game playing algorithms produce high-quality strategies with a fraction of memory and computation required by their offline alternatives. Continual Resolving (CR) is a recent theoretically sound approach to online game playing that has been used to outperform human professionals in poker. However, parts of the algorithm were specific to poker, which enjoys many properties not shared by other imperfect information games. We present a domain-independent formulation of CR applicable to any two-player zero-sum extensive-form games that works with an abstract resolving algorithm. We further describe and implement its Monte Carlo variant (MCCR) which uses Monte Carlo Counterfactual Regret Minimization (MCCFR) as a resolver. We prove the correctness of CR and show an O(T-1/2)-dependence of MCCR's exploitability on the computation time. Furthermore, we present an empirical comparison of MCCR with incremental tree building to Online Outcome Sampling and Information-set MCTS on several domains.