lecture_03_minimax.py

# This file may not be shared/redistributed without permission. Please read copyright notice in the git repo. If this file contains other copyright notices disregard this text.
from irlc.ex01.agent import train
from irlc.pacman.pacman_environment import GymPacmanEnvironment
from irlc.utils.video_monitor import VideoMonitor
from irlc.ex03multisearch.multisearch_agents import GymMinimaxAgent


layout_str = """
%%%%%%%%%
%       %
% %%%%  %
%       %
%   P   %
%%%%    %
%%%% .G %
%%%%    %
%%%%%%%%%
""".strip()

def gminmax(layout='smallClassic', layout_str=layout_str, Agent=None, depth=3, **kwargs):
    zoom = 2
    env = GymPacmanEnvironment(layout=layout, layout_str=layout_str, zoom=zoom, **kwargs)
    agent = Agent(env, depth=depth)
    from irlc import PlayWrapper
    agent = PlayWrapper(agent, env)

    env = VideoMonitor(env, agent=agent, agent_monitor_keys=tuple(), fps=10)
    train(env, agent, num_episodes=30)
    env.close()

if __name__ == "__main__":
    d = 3
    gminmax(layout='minimaxClassic', layout_str=layout_str, Agent=GymMinimaxAgent,depth=d)
    # gminmax(layout='minimaxClassic', layout_str=layout_str, Agent=GymAlphaBetaAgent, depth=d)
    # gminmax(layout='minimaxClassic', layout_str=layout_str, Agent=GymExpectimaxAgent,depth=d)