This repository contains the source code for the experiments presented in Convergence and Stability of Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning, and Online Decision Transformers by Miroslav Štrupl, Oleg Szehr, Francesco Faccio, Dylan R. Ashley, Rupesh Kumar Srivastava, and Jürgen Schmidhuber.
To produce the plots shown in the paper execute the following in a bash shell:
./runAfter execution has completed, a fig folder with .svg files should have been generated.