[Python] RL, 강화학습 Frozen Lake v1 자동실행 하는 방법

https://github.com/ParkGyeongTae/dqn-atari-breakout/tree/main/3_frozenlake_v0

GitHub - ParkGyeongTae/dqn-atari-breakout

 

환경 설정

### Step 1) 아나콘다 가상환경 만들기

conda create -n py37 python=3.7

### Step 2) 가상환경 접속

conda activate py37

### Step 3) 라이브러리 설치

pip install gym==0.23.1
pip install pygame==2.1.2

 

1_frozenlake-v1-example.py

import gym

env = gym.make('FrozenLake-v1', is_slippery = False)

episode_number  = 5
timestep_number = 100

for episode in range(episode_number):
    observation = env.reset()

    for timestep in range(timestep_number):

        env.render()
        action = env.action_space.sample()
        observation, reward, done, info = env.step(action)

        if done:
            env.render()
            print('Episode : {:02d} | Timestep : {:02d} | Rewards : {:02.0f}'.format(episode + 1, timestep + 1, reward))
            break

env.close()

 

python 1_frozenlake-v1-example.py