windyGridworld: Windy Gridworld

In markdumke/reinforcelearn: Reinforcement Learning

Windy Gridworld

Description

Windy Gridworld problem for reinforcement learning. Actions include going left, right, up and down. In each column the wind pushes you up a specific number of steps (for the next action). If an action would take you off the grid, you remain in the previous state. For each step you get a reward of -1, until you reach into a terminal state.

Arguments

...	[any] Arguments passed on to makeEnvironment.

Details

This is the gridworld (goal state denoted G, start state denoted S). The last row specifies the upward wind in each column.

.	.	.	.	.	.	.	.	.	.
.	.	.	.	.	.	.	.	.	.
.	.	.	.	.	.	.	.	.	.
S	.	.	.	.	.	.	G	.	.
.	.	.	.	.	.	.	.	.	.
.	.	.	.	.	.	.	.	.	.
.	.	.	.	.	.	.	.	.	.
.	.	.	.	.	.	.	.	.	.
.	.	.	.	.	.	.	.	.	.
.	.	.	.	.	.	.	.	.	.
0	0	0	1	1	1	2	2	1	0

Usage

makeEnvironment("windy.gridworld", ...)

Methods

• $step(action)
  Take action in environment. Returns a list with state, reward, done.

• $reset()
  Resets the done flag of the environment and returns an initial state. Useful when starting a new episode.

• $visualize()
  Visualizes the environment (if there is a visualization function).

References

Sutton and Barto (Book draft 2017): Reinforcement Learning: An Introduction Example 6.5

Examples

env = makeEnvironment("windy.gridworld")

markdumke/reinforcelearn documentation built on Nov. 17, 2022, 12:53 a.m.