rl_env is is a package containing reinforcement learning (RL) environments.
rl_env is is a package containing reinforcement learning (RL) environments.
These environments include gridworlds, taxi, mountain car, cart-pole, and a simulation of the texas ART car. There are some options to change variables of these environments:
Call env --env type [options]
Env types: taxi tworooms fourrooms energy fuelworld mcar cartpole car2to7 car7to2 carrandom stocks
Options:
--seed value (integer seed for random number generator)
--deterministic (deterministic version of domain)
--stochastic (stochastic version of domain)
--delay value (# steps of action delay (for mcar and tworooms)
--lag (turn on brake lag for car driving domain)
--highvar (have variation fuel costs in Fuel World)
--nsectors value (# sectors for stocks domain)
--nstocks value (# stocks for stocks domain)
--prints (turn on debug printing of actions/rewards)
There are a variety of domains provided in this package. Here are a few examples:
CartPole provides source for the CartPole balancing task.
FuelRooms provides code for the Fuel World task.
RobotCarVel provides code for the car velocity control simulation.