@article{Henderson_Chang_Bacon_Meger_Pineau_Precup_2018, title={OptionGAN: Learning Joint Reward-Policy Options Using Generative Adversarial Inverse Reinforcement Learning}, volume={32}, url={https://ojs.aaai.org/index.php/AAAI/article/view/11775}, DOI={10.1609/aaai.v32i1.11775}, abstractNote={ <p> Reinforcement learning has shown promise in learning policies that can solve complex problems. However, manually specifying a good reward function can be difficult, especially for intricate tasks. Inverse reinforcement learning offers a useful paradigm to learn the underlying reward function directly from expert demonstrations. Yet in reality, the corpus of demonstrations may contain trajectories arising from a diverse set of underlying reward functions rather than a single one. Thus, in inverse reinforcement learning, it is useful to consider such a decomposition. The options framework in reinforcement learning is specifically designed to decompose policies in a similar light. We therefore extend the options framework and propose a method to simultaneously recover reward options in addition to policy options. We leverage adversarial methods to learn joint reward-policy options using only observed expert states. We show that this approach works well in both simple and complex continuous control tasks and shows significant performance increases in one-shot transfer learning. </p> }, number={1}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Henderson, Peter and Chang, Wei-Di and Bacon, Pierre-Luc and Meger, David and Pineau, Joelle and Precup, Doina}, year={2018}, month={Apr.} }