Skip to content

An OpenAI Gym based wrapper for GymCarla. Imitates the rendering mode of the examples for ease of use, modular design for "easy" customization.

Notifications You must be signed in to change notification settings

dosssman/GymCarla

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 

Repository files navigation

Gym Wrapper for Carla 0.9.6

Dependencies and install

Conda env install

Basic usage

import gym
import gym_carla

env = gym.make( 'CarlaDefault-v0', host='localhost', timestep_limit = 10000, render = True, render_mode = 'human')

for ep in range( 10):
  print( "Episode %d:" % ep)
  done = False
  obs = env.reset()

  # print( "# DEBUG: Done before entering episode", done)

  while not done:
    obs, _, done, _ = env.step( env.action_space.sample())
    print( 'Obs at timestep %d: %s' % (env._current_timestep, 'Not none' if obs is not None else 'None'))

    env.render()

env.close()

About

An OpenAI Gym based wrapper for GymCarla. Imitates the rendering mode of the examples for ease of use, modular design for "easy" customization.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages