openai_ros.task_envs.cartpole_stay_up package

Submodules

openai_ros.task_envs.cartpole_stay_up.stay_up module

class openai_ros.task_envs.cartpole_stay_up.stay_up.CartPoleStayUpEnv

Bases: openai_ros.robot_envs.cartpole_env.CartPoleEnv

__init__()

__module__ = 'openai_ros.task_envs.cartpole_stay_up.stay_up'

_compute_reward(observations, done)

Gives more points for staying upright, gets data from given observations to avoid having different data than other previous functions :return:reward

_get_obs()

_init_env_variables()

Inits variables needed to be initialised each time we reset at the start of an episode. :return:

_is_done(observations)

_set_action(action)

_set_init_pose()

Sets joints to initial position [0,0,0] :return:

get_params()

Module contents