Learn R Programming

pomdp (version 1.2.4)

DynaMaze: The Dyna Maze

Description

The Dyna Maze from Chapter 8 of the textbook "Reinforcement Learning: An Introduction."

Arguments

Format

An object of class MDP.

Details

The simple 6x9 maze with a few walls.

References

Richard S. Sutton and Andrew G. Barto (2018). Reinforcement Learning: An Introduction Second Edition, MIT Press, Cambridge, MA.

See Also

Other MDP_examples: Cliff_walking, MDP(), Maze, Windy_gridworld

Other gridworld: Cliff_walking, Maze, Windy_gridworld, gridworld

Other MDP_examples: Cliff_walking, MDP(), Maze, Windy_gridworld

Other gridworld: Cliff_walking, Maze, Windy_gridworld, gridworld

Examples

Run this code
data(DynaMaze)

DynaMaze

gridworld_matrix(DynaMaze)
gridworld_matrix(DynaMaze, what = "labels")

gridworld_plot_transition_graph(DynaMaze)

Run the code above in your browser using DataLab