Code for reproducing "Solving Montezuma's Revenge with Planning and Reinforcement Learning"
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
ALE-montezuma-modified @ c93034c
IW @ 6716723
examine_game
hexq @ 6e985e4
report-TFG @ 143e476
.gitignore
.gitmodules
README.md

README.md

Code used in making the undergraduate thesis "Solving Montezuma's Revenge with Planning and Reinforcement Learning".

  • examine_game: scripts for examining the memory and testing the options.
  • IW: the implementation of IW(3) on position, based on Lipovetzky, Ramirez and Geffner's.
  • hexq: the implementation of Sarsa for the learning results.
  • ALE-montezuma-modified: slightly modified ALE, notably with added rewards to MR and some methods and attributes made public.
  • report-TFG: the thesis report, in LaTeX.

License

Almost all the code here uses the Arcade Learning Environment, which is GPLv2. For simplicity, then, all the code in this repository or its sub-repositories is GPLv2 (see code-license.txt).

The data and document are released under a Creative Commons Attribution 4.0 International License. Creative Commons License