Utility Wrappers: a set of wrappers which provide convenient reusable logic, such as enforcing turn order or clipping out-of-bounds actions. 3. 5 1 1. Model Explanation; leduc-holdem-cfr: Pre-trained CFR (chance sampling) model on Leduc Hold'em: leduc-holdem-rule-v1: Rule-based model for Leduc Hold'em, v1An attempt at a Python implementation of Pluribus, a No-Limits Hold'em Poker Bot - pluribus/README. In addition to NFSP’s main, average strategy profile we also evaluated the best response and greedy-average strategies, which deterministically choose actions that maximise the predicted ac- tion values or probabilities respectively. g. PettingZoo Wrappers#. Environment Setup# To follow this tutorial, you will need to install the dependencies shown below. As heads-up no-limit Texas hold’em is commonly played online for high stakes, the scientific benefit of releasing source code must be balanced with the potential for it to be used for gambling purposes. 01 every time they touch an evader. In addition, we also prove that the weighted average strategy by skipping previous itera- The most popular variant of poker today is Texas hold’em. >> Leduc Hold'em pre-trained model >> Start a new game! >> Agent 1 chooses raise. Leduc Hold’em; Rock Paper Scissors; Texas Hold’em No Limit; Texas Hold’em; Tic Tac Toe; MPE. You can also find the code in examples/run_cfr. leduc-holdem-cfr. Readme License. . At the beginning, both players get two cards. Leduc Hold'em is a smaller version of Limit Texas Hold'em (first introduced in Bayes' Bluff: Opponent Modeling in Poker). 75 times the size of the pursuer radius, while food. Leduc Hold’em (a simplified Te xas Hold’em game), Limit. reset() while env. . GetAway setup using RLCard. The tournaments suggest the pessimistic MaxMin strategy is the best performing and the most robust strat. Leduc Hold'em is a simplified version of Texas Hold'em. leduc-holdem-rule-v1. Extensive-form games are a. It supports various card environments with easy-to-use interfaces, including Blackjack, Leduc Hold'em, Texas Hold'em, UNO, Dou Dizhu and Mahjong. 10^3. 5 2 0 50 100 150 200 250 300 Exploitability Time in s XFP, 6-card Leduc FSP:FQI, 6-card Leduc Figure:Learning curves in Leduc Hold’em. Most environments only give rewards at the end of the games once an agent wins or losses, with a reward of 1 for winning and -1 for losing. Leduc Hold ’Em. Poison has a radius which is 0. Heinrich, Lanctot and Silver Fictitious Self-Play in Extensive-Form Games The game of Leduc hold ’em is this paper but rather a means to demonstrate our approach sufficiently small that we can have a fully parameterized on the large game of Texas hold’em. ipynb","path. In this paper, we provide an overview of the key. This mapping exhibited less exploitability than prior mappings in almost all cases, based on test games such as Leduc Hold’em and Kuhn Poker. '''. Only player 2 can raise a raise. Leduc Hold’em is a poker variant that is similar to Texas Hold’em, which is a game often used in academic research []. Leduc Hold'em은 Texas Hold'em의 단순화 된. . It includes the whole Game-Environment "Leduc Hold'em" which is inspired by the OpenAI Gym-Project. Another round follows. 🤖 An Open Source Texas Hold'em AI Topics. 10^2. . . Leduc Hold’em is a variation of Limit Texas Hold’em with fixed number of 2 players, 2 rounds and a deck of six cards (Jack, Queen, and King in 2 suits). 13 1. proposed instant updates. It extends the code from Training Agents to add CLI (using argparse) and logging (using Tianshou’s Logger). limit-holdem. Return type: (list) Leduc Poker (Southey et al) and Liar’s Dice are two different games that are more tractable than games with larger state spaces like Texas Hold'em while still being intuitive to grasp. get_payoffs ¶ Get the payoff of a game. , & Bowling, M. Confirming the observations of [Ponsen et al. The mean exploitability andSuspicion Agent没有进行任何专门的训练，仅仅利用GPT-4的先验知识和推理能力，就能在Leduc Hold'em等不同的不完全信息游戏中战胜专门针对这些游戏训练的算法，如CFR和NFSP。 这表明大模型具有在不完全信息游戏中取得强大表现的潜力。Abstract One way to create a champion level poker agent is to compute a Nash Equilibrium in an abstract version of the poker game. Solve Leduc Hold Em using cfr. 1 Strategic Decision Making . We will walk through the creation of a simple Rock-Paper-Scissors environment, with example code for both AEC and Parallel environments. . Leduc Hold'em is a simplified version of Texas Hold'em. doc, example. Simple; Simple Adversary; Simple Crypto; Simple Push; Simple Reference; Simple Speaker Listener; Simple Spread; Simple Tag; Simple World Comm; SISL. The players drop their respective token in a column of a standing grid, where each token will fall until it reaches the bottom of the column or reaches an existing token. Training CFR (chance sampling) on Leduc Hold’em¶ To show how we can use step and step_back to traverse the game tree, we provide an example of solving Leduc Hold’em with CFR (chance sampling). . Leduc Hold'em. The ACPC dealer can run other poker games as well. . ciation collusion in Leduc Hold’em poker. class rlcard. InfoSet Number: the number of the information sets; Avg. 5. . In Leduc hold ’em, the deck consists of two suits with three cards in each suit. The Judger class for Leduc Hold’em. Leduc hold'em Poker is a larger version than Khun Poker in which the deck consists of six cards (Bard et al. 77 KBFor our test with Leduc Hold'em poker game we define three scenarios. There is a two bet maximum per round, with raise sizes of 2 and 4 for each round. Each step, they can move and punch. He has always been there toLimit leduc holdem poker(有限注德扑简化版): 文件夹为limit_leduc，写代码的时候为了简化，使用的环境命名为NolimitLeducholdemEnv，但实际上是limitLeducholdemEnv Nolimit leduc holdem poker(无限注德扑简化版): 文件夹为nolimit_leduc_holdem3，使用环境为NolimitLeducholdemEnv（chips=10） Limit. Each pursuer observes a 7 x 7 grid centered around itself, depicted by the orange boxes surrounding the red pursuer agents. Example implementation of the DeepStack algorithm for no-limit Leduc poker - PokerBot-DeepStack-Leduc/readme. It supports various card environments with easy-to-use interfaces, including Blackjack, Leduc Hold’em, Texas Hold’em, UNO, Dou Dizhu and Mahjong. Leduc hold'em Poker is a larger version than Khun Poker in which the deck consists of six cards (Bard et al. When it is played with just two players (heads-up) and with fixed bet sizes and a fixed number of raises (limit), it is called heads-up limit hold’em or HULHE ( 19 ). We will go through this process to have fun!. It boasts a large number of algorithms and high. Most environments only give rewards at the end of the games once an agent wins or losses, with a reward of 1 for winning and -1 for losing. 4 with a fix for texas hold'em no limit; bump version; 1. The deck used in Leduc Hold’em contains six cards, two jacks, two queens and two kings, and is shuffled prior to playing a hand. At the beginning of a hand, each player pays a one chip ante to the pot and receives one private card. Leduc hold'em for 2 players. . If you find this repo useful, you may cite:Update rlcard to v1. Return type: (list)Leduc Poker (Southey et al) and Liar’s Dice are two different games that are more tractable than games with larger state spaces like Texas Hold'em while still being intuitive to grasp. . Firstly, tell “rlcard” that we need a Leduc Hold’em environment. doudizhu-rule-v1. action_space(agent). . The game ends if both players sequentially decide to pass. The deckconsists only two pairs of King, Queen and Jack, six cards in total. Leduc hold’em is a two round game with one private card for each player, and one publicly visible board card that is revealed after the first round of player actions. Returns: list of payoffs. However, we can also define agents. ,2007), which may inspire more subsequent use of LLMs in imperfect-information games. At the end, the player with the best hand wins and. (210, 160, 3) Observation Values. Environment Setup#. To show how we can use step and step_back to traverse the game tree, we provide an example of solving Leduc Hold'em with CFR (chance sampling). The goal of RLCard is to bridge reinforcement learning and imperfect information games, and push. This tutorial is a simple example of how to use Tianshou with a PettingZoo environment. We release all interaction data between Suspicion-Agent and traditional algorithms for imperfect-informationTraining CFR on Leduc Hold'em In this tutorial, we will showcase a more advanced algorithm CFR, which uses step and step_back to traverse the game tree. PettingZoo / tutorials / Ray / rllib_leduc_holdem. It supports various card environments with easy-to-use interfaces, including Blackjack, Leduc Hold'em, Texas Hold'em, UNO, Dou Dizhu and Mahjong. The pursuers have a discrete action space of up, down, left, right and stay. Conversion wrappers# AEC to Parallel#. For this paper, we limit the scope of our experiments to settings with exactly two colluding agents. We have also constructed a smaller version of hold ’em, which seeks to retain the strategic ele-ments of the large game while keeping the size of the game tractable. We have also constructed a smaller version of hold ’em, which seeks to retain the strategic ele-ments of the large game while keeping the size of the game tractable. (0, 255) This is a simple physics based cooperative game where the goal is to move the ball to the left wall of the game border by activating the vertically moving pistons. The objective is to combine 3 or more cards of the same rank or in a sequence of the same suit. Similar to Texas Hold’em, high-rank cards trump low-rank cards, e. Leduc Hold’em is a two player poker game. The results show that Suspicion-Agent can potentially outperform traditional algorithms designed for imperfect information games, without any specialized. The main goal of this toolkit is to bridge the gap between reinforcement learning and imperfect information games. 1. Leduc Hold'em . ### Action Space From the AlphaZero chess paper: > [In AlphaChessZero, the] action space is a 8x8x73 dimensional array. 실행 examples/leduc_holdem_human. Leduc Hold'em에서 CFR 교육; 사전 훈련 된 Leduc 모델로 즐거운 시간 보내기; 단일 에이전트 환경으로서의 Leduc Hold'em; R 예제는 여기 에서 찾을 수 있습니다. Leduc Hold'em is a simplified version of Texas Hold'em. raise_amount = 2: self. small_blind = 1: self. The DeepStack algorithm arises out of a mathematically rigorous approach to approximating Nash equilibria in two-player, zero-sum, imperfect information games. How to Cite Davis, T. Figure 8 shows. An example of Leduc Hold'em is as below:association collusion in Leduc Hold’em poker. Leduc Hold'em is a simplified version of Texas Hold'em. Additionally, we show that SES isTianshou Overview #. . mahjong. The AEC API supports sequential turn based environments, while the Parallel API. . . . 3. This size is two chips in the first betting round and four chips in the second. Note that for both . Find hotels in Leduc from CA $61. We release all interaction data between Suspicion-Agent and traditional algorithms for imperfect-informationState Shape. Each game is fixed with two players, two rounds, two-bet maximum andraise amounts of 2 and 4 in the first and second round. AI Poker Tutorial. reset(). At the beginning of a hand, each player pays a one chip ante to the pot and receives one private card. Limit Hold'em. big_blind = 2 * self. The deck used in Leduc Hold’em contains six cards, two jacks, two queens and two kings, and is shuffled prior to playing a hand. from pettingzoo. (0,255) Entombed’s competitive version is a race to last the longest. The first computer program to outplay human professionals at heads-up no-limit Hold'em poker. . Cite this work. ,2007), which may inspire more subsequent use of LLMs in imperfect-information games. public_card (object) – The public card that seen by all the players. 140 FollowersLeduc Hold’em; Rock Paper Scissors; Texas Hold’em No Limit; Texas Hold’em; Tic Tac Toe; MPE. Similarly, an information state of Leduc Hold’em can be encoded as a vector of length 30, as it contains 6 cards with 3 duplicates, 2 rounds, 0 to 2 raises per round and 3 actions. The code was written in the Ruby Programming Language. PettingZoo includes a wide variety of reference environments, helpful utilities, and tools for creating your own custom environments. We test our method on Leduc Hold’em and five different HUNL subgames generated by DeepStack, the experiment results show that the proposed instant updates technique makes significant improvements against CFR, CFR+, and DCFR. This tutorial shows how to train a Deep Q-Network (DQN) agent on the Leduc Hold’em environment (AEC). Many classic environments have illegal moves in the action space. This tutorial will demonstrate how to use LangChain to create LLM agents that can interact with PettingZoo environments. However, if their choices are different, the winner is determined as follows: rock beats scissors, scissors beat paper, and paper beats rock. Returns: Each entry of the list corresponds to one entry of the. LeducHoldemRuleAgentV1 ¶ Bases: object. We show that our proposed method can detect both assistant and associa-tion collusion. Parameters: players (list) – The list of players who play the game. cfr --cfr_algorithm external --game Leduc. Cepheus - Bot made by the UA CPRG ; you can query and play it. Additionally, we show that SES isLeduc hold'em is a small toy poker game that is commonly used in the poker research community. 01 every time they touch an evader. Table of Contents 1 Introduction 1 1. It supports various card environments with easy-to-use interfaces, including Blackjack, Leduc Hold'em, Texas. - GitHub - JamieMac96/leduc-holdem-using-pomcp: Leduc hold'em is a. Whenever you score a point, you are rewarded +1 and your. Leduc Hold ’Em. Leduc Hold’em is a two player poker game. PettingZoo Wrappers can be used to convert between. Leduc Hold’em . leducholdem_rule_models. . In this paper, we provide an overview of the key components This work centers on UH Leduc Poker, a slightly more complicated variant of Leduc Hold’em Poker. Simple; Simple Adversary; Simple Crypto; Simple Push; Simple Reference; Simple Speaker Listener; Simple Spread; Simple Tag; Simple World Comm; SISL. In the first scenario we model a Neural Fictitious Self Player [26] competing against a random-policy player. Leduc Hold ’Em. You can also find the code in examples/run_cfr. Unlike Texas Hold’em, the actions in DouDizhu can not be easily abstracted, which makes search computationally expensive and commonly used reinforcement learning algorithms less effective. ,2012) when compared to established methods like CFR (Zinkevich et al. . There are two rounds. . cfr --cfr_algorithm external --game Leduc. . Texas Hold'em is a poker game involving 2 players and a regular 52 cards deck. Leduc Hold’em; Rock Paper Scissors; Texas Hold’em No Limit; Texas Hold’em; Tic Tac Toe; MPE. The first reference, being a book, is more helpful and detailed (see Ch. Fig. , 2011], both UCT-based methods initially learned faster than Outcome Sampling but UCT later suf-fered divergent behaviour and failure to converge to a Nash equilibrium. . Leduc Hold'em as Single-Agent Environment. Most of the strong poker AI to date attempt to approximate a Nash equilibria to one degree. No-limit Texas Hold’em (wiki, baike) 10^162. In Leduc Hold’em there is a limit of one bet and one raise per round. RLCard is an open-source toolkit for reinforcement learning research in card games. . {"payload":{"allShortcutsEnabled":false,"fileTree":{"rlcard/games/leducholdem":{"items":[{"name":"__init__. Leduc Hold’em and River poker. ,2007), which may inspire more subsequent use of LLMs in imperfect-information games. py. py. . Leduc Hold’em, and has also been implemented in NLTH, though no experimental results are given for that domain. In Leduc hold ’em, the deck consists of two suits with three cards in each suit. This is a popular way of handling rewards with significant variance of magnitude, especially in Atari environments. The goal of RLCard is to bridge reinforcement learning and imperfect information games, and push forward the. DeepHoldem - Implementation of DeepStack for NLHM, extended from DeepStack-Leduc DeepStack - Latest bot from the UA CPRG. mpe import simple_push_v3 env = simple_push_v3. . , 2005] and Flop Hold’em Poker (FHP) [Brown et al. model, with well-defined priors at every information set. computed strategies for Kuhn Poker and Leduc Hold’em. 2 2 Background 5 2. This value is important for establishing the simplest possible baseline: the random policy. We can know that the Leduc Hold'em environment is a 2-player game with 4 possible actions. . md","path":"README. leduc-holdem-rule-v2. Because not every RL researcher has a game-theory background, the team designed the interfaces to be easy-to-use and the environments to. There is no action feature. Pursuers also receive a reward of 0. . PettingZoo and Pistonball. If you get stuck, you lose. Training CFR (chance sampling) on Leduc Hold’em; Having Fun with Pretrained Leduc Model; Training DMC on Dou Dizhu; Evaluating Agents. md","contentType":"file"},{"name":"adding-models. For more information, see About AEC or PettingZoo: A Standard API for Multi-Agent Reinforcement Learning. utils import average_total_reward from pettingzoo. {"payload":{"allShortcutsEnabled":false,"fileTree":{"":{"items":[{"name":"README. 5. tbd; Follow me on Twitter to get updates when new parts go live. ↳ 15 cells hiddenThe following script uses pytest to test all other PettingZoo environments which support action masking. We show that our proposed method can detect both assistant and association collusion. 데모. This environment has 2 agents and 3 landmarks of different colors. Cooperative pong is a game of simple pong, where the objective is to keep the ball in play for the longest time. to bridge reinforcement learning and imperfect information games. For NLTH, it is implemented by rst solving the game in a coarse abstraction, then xing the strategies for the pre-op ( rst) round, and re-solving for certain endgames start-ing at the op (second round) after common pre op bet-For example, heads-up Texas Hold’em has 1018 game states and requires over two petabytes of storage to record a single strategy1. This tutorial is a full example using Tianshou to train a Deep Q-Network (DQN) agent on the Tic-Tac-Toe environment. Returns: A dictionary of all the perfect information of the current state. using two different heads-up limit poker variations: a small-scale variation called Leduc Hold’em, and a full-scale one called Texas Hold’em. It is played with a deck of six cards, comprising two suits of three ranks each (often. This documentation overviews creating new environments and relevant useful wrappers, utilities and tests included in PettingZoo designed for the creation of new environments. Tianshou: Basic API Usage#. from rlcard import models. . Fictitious Self-Play in Leduc Hold’em 0 0. 在Leduc Hold'em是双人游戏, 共有6张卡牌: J, Q, K各两张. ,2017]techniques to automatically construct different collusive strategies for both environments. Leduc Hold ’Em. . 2 Kuhn Poker and Leduc Hold’em. We will also introduce a more flexible way of modelling game states. At the beginning of the game, each player receives one card and, after betting, one public card is revealed. . 3. Find your family's origin in Canada, average life expectancy, most common occupation, and. Search for another surname. You should see 100 hands played, and at the end, the cumulative winnings of the players. . , 2005] and Flop Hold’em Poker (FHP) [Brown et al. Leduc No. The library currently implements vanilla CFR [1], Chance Sampling (CS) CFR [1,2], Outcome Sampling (CS) CFR [2], and Public Chance Sampling (PCS) CFR [3]. We have shown, it is a hard task to nd global optima for Stackelberg equilibrium, even the three-player Kuhn Poker. We evaluate SoG on four games: chess, Go, heads-up no-limit Texas hold’em poker, and Scotland Yard. It is played with a deck of six cards, comprising two suits of three ranks each (often the king, queen, and jack - in our implementation, the ace, king, and queen). Pursuers also receive a reward of 0. In the rst round a single private card is dealt to each. 1 Contributions . This is essentially the same one I am using for my. 0. The goal of RLCard is to bridge reinforcement learning and imperfect information games, and push forward the research of reinforcement learning in domains with multiple agents, large. In the rst round a single private card is dealt to each. Leduc Hold’em is a simplified version of Texas Hold’em. To install the dependencies for one family, use pip install pettingzoo [atari], or use pip install pettingzoo [all] to install all dependencies. The game begins with each player being dealt. To follow this tutorial, you will need to. Toggle navigation of MPE. The Kuhn poker is a one-round poker, where the winner is determined by the highest card. Alice and Bob are rewarded +2 if Bob reconstructs the message, but are. Contribute to achahalrsh/rlcard-getaway development by creating an account on GitHub. There are two rounds. @article{terry2021pettingzoo, title={Pettingzoo: Gym for multi-agent reinforcement learning}, author={Terry, J and Black, Benjamin and Grammel, Nathaniel and Jayakumar, Mario and Hari, Ananth and Sullivan, Ryan and Santos, Luis S and Dieffendahl, Clemens and Horsch, Caroline and Perez-Vicente, Rodrigo and others}, journal={Advances in Neural. Limit Hold'em. The resulting strategy is then used to play in the full game. There are two agents (paddles), one that moves along the left edge and the other that moves along the right edge of the screen. Leduc Hold ‘em rule model. It is shown how minimizing counterfactual regret minimizes overall regret, and therefore in self-play can be used to compute a Nash equilibrium, and is demonstrated in the domain of poker, showing it can solve abstractions of limit Texas Hold'em with as many as 1012 states, two orders of magnitude larger than previous methods. No-limit Texas Hold'em","No-limit Texas Hold'em has similar rule with Limit Texas Hold'em. This Project is based on Heinrich and Silvers Work "Neural Fictitious Self-Play in Imperfect Information Games". December 2017; Microsystems Electronics and Acoustics 22(5):63-72;. . Leduc Hold’em; Rock Paper Scissors; Texas Hold’em No Limit; Texas Hold’em; Tic Tac Toe; MPE. Combat ’s plane mode is an adversarial game where timing, positioning, and keeping track of your opponent’s complex movements are key. {"payload":{"allShortcutsEnabled":false,"fileTree":{"tutorials/Ray":{"items":[{"name":"render_rllib_leduc_holdem. #Each player automatically puts 1 chip into the pot to begin the hand (called an ante) #This is followed by the first round (called preflop) of betting. Smooth UCT, on the other hand, continued to approach a Nash equilibrium, but was eventually overtakenReinforcement Learning. 13 1. from pettingzoo. Along with our Science paper on solving heads-up limit hold'em, we also open-sourced our code link. . Fictitious Self-Play in Leduc Hold’em 0 0. To evaluate the al-gorithm’s performance, we achieve a high-performance and Leduc Hold’em — Illegal action masking, turn based actions. . Work in Progress! Intro. Thus, any single-agent algorithm can be connected to the environment. See the documentation for more information. A solution to the smaller abstract game can be computed and isThe thesis introduces an analysis of counterfactual regret minimisation (CFR), an algorithm for solving extensive-form games, and presents tighter regret bounds that describe the rate of progress, as well as presenting a series of theoretical tools for using decomposition, and creating algorithms which operate on small portions of a game at a. For example, heads-up Texas Hold’em has 1018 game states and requires over two petabytes of storage to record a single strategy1. Leduc Hold'em is a toy poker game sometimes used in academic research (first introduced in Bayes' Bluff: Opponent Modeling in Poker). Test your understanding by implementing CFR (or CFR+ / CFR-D) to solve one of these two games in your favorite programming language. Acknowledgements I would like to thank my supervisor, Dr. . Dou Dizhu (wiki, baike). games: Leduc Hold’em [Southey et al. Poker. There is no action feature. Leduc Hold’em, Texas Hold’em, UNO, Dou Dizhu and Mahjong. Reinforcement Learning. Leduc Hold’em : 10^2 : 10^2 : 10^0 : leduc-holdem : 文档, 释例 : 限注德州扑克 Limit Texas Hold'em (wiki, 百科) : 10^14 : 10^3 : 10^0 : limit-holdem : 文档, 释例 : 斗地主 Dou Dizhu (wiki, 百科) : 10^53 ~ 10^83 : 10^23 : 10^4 : doudizhu : 文档, 释例 : 麻将 Mahjong. #. . The AEC API supports sequential turn based environments, while the Parallel API. . In the first round. DeepStack is an artificial intelligence agent designed by a joint team from the University of Alberta, Charles University, and Czech Technical University. It supports various card environments with easy-to-use interfaces, including Blackjack, Leduc Hold’em, Texas Hold’em, and many more. The second round consists of a post-flop betting round after one board card is dealt. View leduc2. 10^2. Toggle navigation of MPE. HULHE was popularized by a series of high-stakes games chronicled in the book The Professor, the Banker, and the. First, let’s define Leduc Hold’em game. The goal of this thesis work is the design, implementation, and evaluation of an intelligent agent for UH Leduc Poker, relying on a reinforcement learning approach. . 11. . 10^0. doc, example. . -Fixed Go and Chess observation spaces, bumped. The comments are designed to help you understand how to use PettingZoo with CleanRL. You can try other environments as well. Example implementation of the DeepStack algorithm for no-limit Leduc poker - MIB/readme. . 1 Strategic Decision Making . Firstly, tell “rlcard” that we need a Leduc Hold’em environment. This tutorial shows how to train a Deep Q-Network (DQN) agent on the Leduc Hold’em environment (AEC). 3. It supports various card environments with easy-to-use interfaces, including Blackjack, Leduc Hold'em, Texas Hold'em, UNO, Dou Dizhu and Mahjong. A round of betting then takes place starting with player one. Step 1: Make the environment. (560, 880, 3) State Values. At the beginning, both players get two cards. Rule. Texas Hold’em is a poker game involving 2 players and a regular 52 cards deck. Leduc Hold'em. For more information, see About AEC or PettingZoo: A Standard API for Multi-Agent Reinforcement Learning. py to play with the pre-trained Leduc Hold'em model. It supports various card environments with easy-to-use interfaces, including Blackjack, Leduc Hold’em, Texas Hold’em, UNO, Dou Dizhu and Mahjong. The white player follows by placing a stone of their own, aiming to either surround more territory than their opponent or capture the opponent’s stones. This documentation overviews creating new environments and relevant useful wrappers, utilities and tests included in PettingZoo designed for the creation of new environments. We investigate the convergence of NFSP to a Nash equilibrium in Kuhn poker and Leduc Hold’em games with more than two players by measuring the exploitability rate of learned strategy profiles. Leduc Hold'em is a simplified version of Texas Hold'em.