728x90
자율주행을 강화학습으로 해보고 싶은 사람들에게 유용한 환경일 것 같아서 공유합니다.

https://decisionforce.github.io/pgdrive/

github.com/decisionforce/pgdrive/releases/download/pgdrive-0.1.1/BIG.mp4
| paper | code |
| arxiv.org/pdf/2012.13681.pdf | github.com/decisionforce/pgdrive |
import pgdrive # Import this package to register the environment!
import gym
env = gym.make("PGDrive-v0", config=dict(use_render=True))
# env = pgdrive.PGDriveEnv(config=dict(environment_num=100)) # Or build environment from class
env.reset()
for i in range(1000):
obs, reward, done, info = env.step(env.action_space.sample()) # Use random policy
env.render()
if done:
env.reset()
env.close()
simple car env
https://github.com/eleurent/highway-env
'관심있는 주제 > RL' 카테고리의 다른 글
| [Review] CURL: Contrastive Unsupervised Representations for Reinforcement Learning (0) | 2021.02.13 |
|---|---|
| Bellman Equation (Value Function, Q Function) 써보기 (0) | 2021.01.16 |
| [Research] Action Space 관련 자료 조사 (0) | 2021.01.03 |
| [Review] Imitation Learning with Concurrent Actions in 3D Games (0) | 2021.01.03 |
| [Review] POMO: Policy Optimization with Multiple Optimafor Reinforcement Learnin (0) | 2020.12.18 |