TempoRL-experiment data

Learning curve data, as well as commands to generate the data and final trained policies of all experiments of the TempoRL paper.

Readme.md -> Contains description of the folder structures in all three archives

experiments.tar.gz -> Archive containing all experiment results with the following folders:

atari -> Contains all results on Atari games

featurized_results -> Contains results on LunarLander-v2 and MountainCar-v0

tabular_results -> Contains results for the tabular experiments.

DDPG results have been added in a separate zip

tempoCar1.mp4 and tempoCar2.mp4 show learned policies of tempoRL in the mountain car environment. The agent blinks bright blue when it decides to make a new decision.

tempoQBert.mp4 shows a tempoRL policy in action on QBert.