Analysis of Bluffing by DQN and CFR in Leduc Hold'em Poker

• URL: http://arxiv.org/abs/2509.04125v1
• Date: Thu, 04 Sep 2025 11:40:24 GMT
• Title: Analysis of Bluffing by DQN and CFR in Leduc Hold'em Poker
• Abstract summary: We study whether two popular algorithms, DQN and CFR, exhibit bluffing behavior in Leduc Hold'em.<n>We find that both DQN and CFR exhibit bluffing behavior, but they do so in different ways.<n>This suggests bluffing is an essential aspect of the game, not of the algorithm.
• Score: 0.3459227740065624
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In the game of poker, being unpredictable, or bluffing, is an essential skill. When humans play poker, they bluff. However, most works on computer-poker focus on performance metrics such as win rates, while bluffing is overlooked. In this paper we study whether two popular algorithms, DQN (based on reinforcement learning) and CFR (based on game theory), exhibit bluffing behavior in Leduc Hold'em, a simplified version of poker. We designed an experiment where we let the DQN and CFR agent play against each other while we log their actions. We find that both DQN and CFR exhibit bluffing behavior, but they do so in different ways. Although both attempt to perform bluffs at different rates, the percentage of successful bluffs (where the opponent folds) is roughly the same. This suggests that bluffing is an essential aspect of the game, not of the algorithm. Future work should look at different bluffing styles and at the full game of poker. Code at https://github.com/TarikZ03/Bluffing-by-DQN-and-CFR-in-Leduc-Hold-em-Poker-Codebase.

Related papers

• Adversarial Learning in Games with Bandit Feedback: Logarithmic Pure-Strategy Maximin Regret [64.73231630190121]
  Learning to play zero-sum games is a fundamental problem in game theory and machine learning.<n>We investigate adversarial learning in zero-sum games under bandit feedback, aiming to minimize the deficit against the maximin pure strategy.<n>We show that the Tsallis-INF algorithm achieves $O(c log T)$ instance-dependent regret with a game-dependent parameter $c$.
  arXiv  Detail & Related papers  (2026-02-06T03:26:01Z)
• How Far Are LLMs from Professional Poker Players? Revisiting Game-Theoretic Reasoning with Agentic Tool Use [52.394999779049606]
  Large Language Models (LLMs) are increasingly applied in high-stakes domains.<n>LLMs fail to compete against traditional algorithms.<n>We propose ToolPoker, a tool-integrated reasoning framework.
  arXiv  Detail & Related papers  (2026-01-31T05:45:25Z)
• SpinGPT: A Large-Language-Model Approach to Playing Poker Correctly [2.5788559173418357]
  We present SpinGPT, the first Large Language Models tailored to Spin & Go, a popular three-player online poker format.<n>Our results show that SpinGPT matches the solver's actions in 78% of decisions (tolerant accuracy)<n>These results suggest that LLMs could be a new way to deal with multi-player imperfect-information games like poker.
  arXiv  Detail & Related papers  (2025-09-26T14:15:44Z)
• General search techniques without common knowledge for imperfect-information games, and application to superhuman Fog of War chess [68.20244032271847]
  We present Obscuro, the first superhuman AI for Fog of War chess.<n>It introduces advances to search in imperfect-information games, enabling strong, scalable reasoning.<n>Experiments against the prior state-of-the-art AI and human players show that Obscuro is significantly stronger.
  arXiv  Detail & Related papers  (2025-06-02T01:41:27Z)
• PokerBench: Training Large Language Models to become Professional Poker Players [3.934572858193348]
  We introduce PokerBench, a benchmark for evaluating the poker-playing abilities of large language models (LLMs)<n> Poker, an incomplete information game, demands a multitude of skills such as mathematics, reasoning, planning, strategy, and a deep understanding of game theory and human psychology.<n> PokerBench consists of a comprehensive compilation of 11,000 most important scenarios, split between pre-flop and post-flop play.
  arXiv  Detail & Related papers  (2025-01-14T18:59:03Z)
• Instruction-Driven Game Engine: A Poker Case Study [53.689520884467065]
  The IDGE project aims to democratize game development by enabling a large language model to follow free-form game descriptions and generate game-play processes. We train the IDGE in a curriculum manner that progressively increases its exposure to complex scenarios. Our initial progress lies in developing an IDGE for Poker, which not only supports a wide range of poker variants but also allows for highly individualized new poker games through natural language inputs.
  arXiv  Detail & Related papers  (2024-10-17T11:16:27Z)
• PokerGPT: An End-to-End Lightweight Solver for Multi-Player Texas Hold'em via Large Language Model [14.14786217204364]
  Poker, also known as Texas Hold'em, has always been a typical research target within imperfect information games (IIGs) We introduce PokerGPT, an end-to-end solver for playing Texas Hold'em with arbitrary number of players and gaining high win rates.
  arXiv  Detail & Related papers  (2024-01-04T13:27:50Z)
• A Survey on Game Theory Optimal Poker [0.0]
  No non-trivial imperfect information game has been solved to date. This makes poker a great test bed for Artificial Intelligence research. We discuss the intricacies of abstraction techniques, betting models, and specific strategies employed by successful poker bots.
  arXiv  Detail & Related papers  (2024-01-02T04:19:25Z)
• Are ChatGPT and GPT-4 Good Poker Players? -- A Pre-Flop Analysis [3.4111723103928173]
  We put ChatGPT and GPT-4 through the poker test and evaluate their poker skills. Our findings reveal that while both models display an advanced understanding of poker, both ChatGPT and GPT-4 are NOT game theory optimal poker players.
  arXiv  Detail & Related papers  (2023-08-23T23:16:35Z)
• CFR-p: Counterfactual Regret Minimization with Hierarchical Policy Abstraction, and its Application to Two-player Mahjong [2.741266294612776]
  We study two-player Mahjong by conducting game theoretical analysis and making a hierarchical abstraction to CFR based on winning policies. This framework can be generalized to other imperfect information games.
  arXiv  Detail & Related papers  (2023-07-22T14:38:47Z)
• DecisionHoldem: Safe Depth-Limited Solving With Diverse Opponents for Imperfect-Information Games [31.26667266662521]
  DecisionHoldem is a high-level AI for heads-up no-limit Texas hold'em with safe depth-limited subgame solving. We release the source codes and tools of DecisionHoldem to promote AI development in imperfect-information games.
  arXiv  Detail & Related papers  (2022-01-27T15:35:49Z)
• Revisiting Game Representations: The Hidden Costs of Efficiency in Sequential Decision-making Algorithms [0.6749750044497732]
  Recent advancements in algorithms for sequential decision-making under imperfect information have shown remarkable success in large games. These algorithms traditionally formalize the games using the extensive-form game formalism. We show that a popular workaround involves using a specialized representation based on player specific information-state trees.
  arXiv  Detail & Related papers  (2021-12-20T22:34:19Z)
• Learning to Play Sequential Games versus Unknown Opponents [93.8672371143881]
  We consider a repeated sequential game between a learner, who plays first, and an opponent who responds to the chosen action. We propose a novel algorithm for the learner when playing against an adversarial sequence of opponents. Our results include algorithm's regret guarantees that depend on the regularity of the opponent's response.
  arXiv  Detail & Related papers  (2020-07-10T09:33:05Z)
• Efficient exploration of zero-sum stochastic games [83.28949556413717]
  We investigate the increasingly important and common game-solving setting where we do not have an explicit description of the game but only oracle access to it through gameplay. During a limited-duration learning phase, the algorithm can control the actions of both players in order to try to learn the game and how to play it well. Our motivation is to quickly learn strategies that have low exploitability in situations where evaluating the payoffs of a queried strategy profile is costly.
  arXiv  Detail & Related papers  (2020-02-24T20:30:38Z)
• Provable Self-Play Algorithms for Competitive Reinforcement Learning [48.12602400021397]
  We study self-play in competitive reinforcement learning under the setting of Markov games. We show that a self-play algorithm achieves regret $tildemathcalO(sqrtT)$ after playing $T$ steps of the game. We also introduce an explore-then-exploit style algorithm, which achieves a slightly worse regret $tildemathcalO(T2/3)$, but is guaranteed to run in time even in the worst case.
  arXiv  Detail & Related papers  (2020-02-10T18:44:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.