Design Principles

The toolkit wraps each game by Env class with easy-to-use interfaces. The goal of this toolkit is to enable the users to focus on algorithm development without caring about the environment. The following design principles are applied when developing the toolkit:

  • Reproducible. Results on the environments can be reproduced. The same result should be obtained with the same random seed in different runs.

  • Accessible. The experiences are collected and well organized after each game with easy-to-use interfaces. Uses can conveniently configure state representation, action encoding, reward design, or even the game rules.

  • Scalable. New card environments can be added conveniently into the toolkit with the above design principles. We also try to minimize the dependencies in the toolkit so that the codes can be easily maintained.

RLCard High-level Design

This document introduces the high-level design for the environments, the games, and the agents (algorithms).


We wrap each game with an Env class. The responsibility of Env is to help you generate trajectories of the games. For developing Reinforcement Learning (RL) algorithms, we recommend to use the following interfaces:

  • set_agents: This function tells the Env what agents will be used to perform actions in the game. Different games may have a different number of agents. The input of the function is a list of Agent class. For example, env.set_agent([RandomAgent(num_actions=env.num_actions) for _ in range(2)]) indicates that two random agents will be used to generate the trajectories.

  • run: After setting the agents, this interface will run a complete trajectory of the game, calculate the reward for each transition, and reorganize the data so that it can be directly fed into a RL algorithm.

For advanced access to the environment, such as traversal of the game tree, we provide the following interfaces:

  • step: Given the current state, the environment takes one step forward, and returns the next state and the next player.

  • step_back: Takes one step backward. The environment will restore to the last state. The step_back is defaultly turned off since it requires expensively recoeding previous states. To turn it on, set allow_step_back = True when make environments.

  • get_payoffs: At the end of the game, this function can be called to obtain the payoffs for each player.


Card games usually have similar structures. We abstract some concepts in card games and follow the same design pattern. In this way, users/developers can easily dig into the code and change the rules for research purpose. Specifically, the following classes are used in all the games:

  • Game: A game is defined as a complete sequence starting from one of the non-terminal states to a terminal state.

  • Round: A round is a part of the sequence of a game. Most card games can be naturally divided into multiple rounds.

  • Dealer: A dealer is responsible for shuffling and allocating a deck of cards.

  • Judger: A judger is responsible for making major decisions at the end of a round or a game.

  • Player: A player is a role who plays cards following a strategy.

To summarize, in one Game, a Dealer deals the cards for each Player. In each Round of the game, a Judger will make major decisions about the next round and the payoffs in the end of the game.


We provide examples of several representative algorithms and wrap them as Agent to show how a learning algorithm can be connected to the toolkit. The first example is DQN which is a representative of the Reinforcement Learning (RL) algorithms category. The second example is NFSP which is a representative of the Reinforcement Learning (RL) with self-play. We also provide CFR (chance sampling) and DeepCFR which belong to Conterfactual Regret Minimization (CFR) category. Other algorithms from these three categories can be connected in similar ways.