seldonian.RL.environments.n_step_mountaincar.N_step_mountaincar

class N_step_mountaincar

Bases: Environment

__init__()

Extends the classic Mountaincar environment such that each action is taken n_steps times instead of once. Refer to mountaincar.Mountaincar docstring.

Variables:
  • n_steps (int) – The number of repeated steps to take following a single action.

  • mc_env – An instance of the Mountaincar class.

  • env_description (Env_Description) – contains attributes describing the environment

  • terminal_state (bool) – Whether the terminal obs is occupied

  • gamma – The discount factor, hardcoded to 1.

__repr__()

Return repr(self).

Methods

get_env_description()

Get environment description. Override this method in child class implementation

get_observation()

Wrapper to get the position and velocity of the cart from the Mountain car environment.

reset()

Go back to initial obs and timestep

start_visualizing()

Turn on visualization debugger.

stop_visualizing()

Turn off visualization debugger.

terminated()

Get the terminal observation

transition(action)

Transition between states given an action, return a reward.

Parameters:

action – A possible action at the current obs

Returns:

reward for reaching the next obs

visualize()

Print out current observation, useful for debugging. Override this method in child class implementation