Welcome to 7Wonder-RL-Lib’s documentation!¶
Readme File¶
7Wonder-RL-Lib¶
Library providing environment for testing Reinforcement learning in 7 Wonders Game.
Overview¶
There are multiple environments for the AI game testing. However, environments implemented now are mostly covered only the traditional board games (Go, Chess, etc.) or 52-card based card games (Poker, Rummy, etc.) where games do not really have interactions with other players.
Most of the Euro-games board games are good game environments to test the algorithm on as there are many aspects to explore, such as tradings, dealing with imperfect informations, stochastic elements, etc.
7 Wonders board games introduced multiple elements mentioned above which are good for testing out new algorithm. This library will cover basic game systems and allow users to customize the environments with custom state space and rewarding systems.
Installation¶
To install the gym environment, run
make develop
make build
make install
Usage¶
Example codes of how to declare the gym environment is displayed below
import SevenWonEnv
from SevenWonEnv.envs.mainGameEnv import Personality
env = gym.make("SevenWonderEnv", player=4) #Declare Environment with 4 Players
To use the Personality that is given (RandomAI, RuleBasedAI, DQNAI, Human), use setPersonality(personalityList)
personalityList = []
personalityList.append(Personality.DQNAI)
for i in range(1, 4):
personalityList.append(Personality.RandomAI)
env.setPersonality(personalityList)
To run the game each step,
stateList = env.step(None)
The variable stateList consist of n 4-tuple, depends on number of players. Each tuple are (new_state, reward, done, info).
To add the custom model, change the SevenWondersEnv/SevenWonEnv/envs/mainGameEnv/Personality.py
file.
Each personality will have 2 main functions, which are init and make_choice.
For example, RandomAI takes all possible choices and randomly choose one choice.
class RandomAI(Personality):
def __init__(self):
super().__init__()
def make_choice(self, player, age, options):
return random.choice(range(len(options)))
Documentation¶
- class SevenWonEnv.envs.SevenWonderEnv.SevenWonderEnv(player)¶
- close()¶
After the user has finished using the environment, close contains the code necessary to “clean up” the environment.
This is critical for closing rendering windows, database or HTTP connections.
- legalAction(playerNum)¶
Given the player number, return all legal actions as a list of action code
- Args:
playerNum: The position of player (1-n)
- Returns:
List[actionCode]
- render(mode='human')¶
Compute the render frames as specified by
render_mode
during the initialization of the environment.The environment’s
metadata
render modes (env.metadata[“render_modes”]) should contain the possible ways to implement the render modes. In addition, list versions for most render modes is achieved through gymnasium.make which automatically applies a wrapper to collect rendered frames.- Note:
As the
render_mode
is known during__init__
, the objects used to render the environment state should be initialised in__init__
.
By convention, if the
render_mode
is:None (default): no render is computed.
“human”: The environment is continuously rendered in the current display or terminal, usually for human consumption. This rendering should occur during
step()
andrender()
doesn’t need to be called. ReturnsNone
.“rgb_array”: Return a single frame representing the current state of the environment. A frame is a
np.ndarray
with shape(x, y, 3)
representing RGB values for an x-by-y pixel image.“ansi”: Return a strings (
str
) orStringIO.StringIO
containing a terminal-style text representation for each time step. The text can include newlines and ANSI escape sequences (e.g. for colors).“rgb_array_list” and “ansi_list”: List based version of render modes are possible (except Human) through the wrapper,
gymnasium.wrappers.RenderCollection
that is automatically applied duringgymnasium.make(..., render_mode="rgb_array_list")
. The frames collected are popped afterrender()
is called orreset()
.
- Note:
Make sure that your class’s
metadata
"render_modes"
key includes the list of supported modes.
Changed in version 0.25.0: The render function was changed to no longer accept parameters, rather these parameters should be specified in the environment initialised, i.e.,
gymnasium.make("CartPole-v1", render_mode="human")
- reset(seed=None, options=None)¶
Reset the environment after each episode
- Args:
seed: Seed ID for randomization options: Default to None
- Returns:
List[State]
- setPersonality(personalityList)¶
Set the personality for each player.
- Args:
personalityList: List[Personality]
- step(action)¶
Proceed one turn of the game.
- Args:
action: 0 by default.
- Returns:
List[tuple] containing (new_state, reward, done, info)