An attempt at implementing the taxi reinforcement learning problem via OO-MDP mostly as described in :
C. G. D. Wasser, An Object-oriented Representation for Efficient Reinforcement Learning. 2010. http://citeseerx.ist.psu.edu/viewdoc/download;jsessionid=66852C019CC187E43E2A2AF207C721D9?doi=10.1.1.415.6106&rep=rep1&type=pdf
This is working towards understanding DOORmax :
Diuk, Carlos, Andre Cohen, and Michael L. Littman. "An object-oriented representation for efficient reinforcement learning." Proceedings of the 25th international conference on Machine learning. ACM, 2008.
http://carlosdiuk.github.io/papers/OORL.pdf
So that I may, one day, comprehend this :
K. Kansky et al., “Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics,” arXiv:1706.04317 [cs], Jun. 2017.