[Python] 강화학습 예제, CartPole-v1 행동 이후의 관찰값 확인

https://github.com/ParkGyeongTae/dqn-atari-breakout/tree/main/1_cartpole-v1-example

GitHub - ParkGyeongTae/dqn-atari-breakout

 

## 사용방법

### 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

 

7_cartpole-v1-observation-action.py

import gym

env = gym.make('CartPole-v1')

observation = env.reset()
print("1 :", observation)

observation, reward, done, info = env.step(0)
# observation, reward, done, info = env.step(1)
print("2 :", observation)

env.close()

 

python 7_cartpole-v1-observation-action.py

 

7_cartpole-v1-observation-action.py

import gym

env = gym.make('CartPole-v1')

observation = env.reset()
print("1 :", observation)

observation, reward, done, info = env.step(0)
# observation, reward, done, info = env.step(1)
print("2 :", observation)

observation, reward, done, info = env.step(0)
# observation, reward, done, info = env.step(1)
print("3 :", observation)

observation, reward, done, info = env.step(0)
# observation, reward, done, info = env.step(1)
print("4 :", observation)

env.close()

 

python 7_cartpole-v1-observation-action.py

 

'''

import gym

env = gym.make('CartPole-v1')

# 에피소드 실행
observation = env.reset()

# 처음 관찰값
print(observation)

# 0이라는 행동을 실행
observation, reward, done, info = env.step(0)

# 행동 이후 관찰값
print(observation)

env.close()

# 결과
# [0.00967408  0.04968553 -0.01428431 -0.00555329]
# [0.01066779 -0.14522868 -0.01439537  0.28258875]

'''