2018 Project on Lifelong Learning from Demonstration
This repository contains the code used to generate results for the NeurIPS-18 paper Lifelong Inverse Reinforcement Learning [1].
The main algorithm implementation is in the ELIRL directory, while support for cross-domain transfer is in the ELIRL_CrossDomain directory.
The results from the paper can be replicated by running the relevant files from the ELIRL_testing directory.
If you use this code, please cite [1].
[1] Mendez, Jorge A., Shivkumar, Shashank, and Eaton, Eric. Lifelong Inverse Reinforcement Learning. Advances in Neural Information Processing Systems 31 (NeurIPS-18), 2018