mlsanityData to 13 Oct 2026

Depth-Limited Solving for Imperfect-Information Games

arXiv 1805.08195 ↗First posted 21 May 2018cs.GT cs.AI cs.MAcited by 24

Not on the map. Why?

Abstract (arXiv)

A fundamental challenge in imperfect-information games is that states do not have well-defined values. As a result, depth-limited search algorithms used in single-agent settings and perfect-information games do not apply. This paper introduces a principled way to conduct depth-limited solving in imperfect-information games by allowing the opponent to choose among a number of strategies for the remainder of the game at the depth limit. Each one of these strategies results in a different set of values for leaf nodes. This forces an agent to be robust to the different strategies an opponent may employ. We demonstrate the effectiveness of this approach by building a master-level heads-up no-limit Texas hold'em poker AI that defeats two prior top agents using only a 4-core CPU and 16 GB of memory. Developing such a powerful agent would have previously required a supercomputer.

Key facts. Cited by 24 papers in the map (data through 13 Oct 2026). First posted on arXiv 21 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 1; 2022: 4; 2023: 6; 2024: 5; 2025: 3; 2026: 5.

24 papers.

Sort:

By area:

  1. 2022ESCHER: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate Regretcited by 24
  2. 2024PokerGPT: An End-to-End Lightweight Solver for Multi-Player Texas Hold'em via Large Language Modelcited by 20
  3. 2021Neural Recursive Belief States in Multi-Agent Reinforcement Learningcited by 18
  4. 2024Policy Space Response Oracles: A Surveycited by 10
  5. 2024RL-CFR: Improving Action Abstraction for Imperfect Information Extensive-Form Games with Reinforcement Learningcited by 10
  6. 2024Minimizing Weighted Counterfactual Regret with Optimistic Online Mirror Descentcited by 7
  7. 2025Scalable Decision Making for Games of Imperfect Informationcited by 7
  8. 2022A Marriage between Adversarial Team Games and 2-player Games: Enabling Abstractions, No-regret Learning, and Subgame Solvingcited by 6
  9. 2023Abstracting Imperfect Information Away from Two-Player Zero-Sum Gamescited by 6
  10. 2026Real-Time Parallel Counterfactual Regret Minimizationcited by 6
  11. 2025General search techniques without common knowledge for imperfect-information games, and application to superhuman Fog of War chesscited by 5
  12. 2026PokerSkill: LLMs Can Play Expert-Level Poker without Training or Solverscited by 5
12 more
  1. 2023Hierarchical Deep Counterfactual Regret Minimizationcited by 4
  2. 2026Agents That Certify Their Own Exploits: Confidence-Scheduled Restricted Responses for Safe Opponent Exploitationcited by 4
  3. 2022A Survey of Decision Making in Adversarial Gamescited by 3
  4. 2025Look-ahead Reasoning with a Learned Model in Imperfect Information Gamescited by 1
  5. 2026AV-AIVAT: 74x Cheaper Agent Evaluation with Certified Anytime-Valid Stopping in Imperfect-Information Gamescited by 1
  6. 2022DecisionHoldem: Safe Depth-Limited Solving With Diverse Opponents for Imperfect-Information Gamescited by 0
  7. 2023Methods and Mechanisms for Interactive Novelty Handling in Adversarial Environmentscited by 0
  8. 2023Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbationscited by 0
  9. 2023AI planning in the imagination: High-level planning on learned abstract search spacescited by 0
  10. 2023Accelerating Nash Equilibrium Convergence in Monte Carlo Settings Through Counterfactual Value Based Fictitious Playcited by 0
  11. 2024AlphaZeroES: Direct score maximization outperforms planning loss minimizationcited by 0
  12. 2026GPU-CFR: 80x Faster Counterfactual Regret Minimization by Compiling the Game to Static Dataflow and CUDA Graph Replaycited by 0