I am trying to connect an agent(GazeboCircuit2TurtlebotLidar-v0) from gym-gazebo library(gym-gazebo is an extension of the initial OpenAI gym for robotics using ROS and Gazebo, an advanced 3D modeling and rendering tool) with a deep reinforcement algorithm(DQN). By referring to the documentations I created a catkin workspace and i cloned that library to local then ran the Turtlebot env using ROS(Noetic) and gazebo(version 11.10.2). BLOCKER - I'm trying to export GazeboCircuit2TurtlebotLidar as a custom env to my algorithm. I could not import gym-gazebo as typical gym env.
SAMPLE CODES:
//registar as a custom env
from gym.envs.registration import register
...
register(
id='GazeboCircuit2TurtlebotLidar-v0',
entry_point='gym_gazebo.envs.turtlebot:GazeboCircuit2TurtlebotLidarEnv',
# More arguments here
)
...
//import to dqn
from gym_gazebo.envs import gazebo_env
env = gym.make('GazeboCircuit2TurtlebotLidar-v0')
Does anyone has any idea regarding this robotic simulation issue as i am a beginner in this domain?