1. Neuronlike adaptive elements that can solve difficult learning control problems
2. Dynamic Programming
3. Borsa, D., Graepel, T. & Shawe-Taylor, J. (2016). Learning shared representations in multi-task reinforcement learning. Retrieved from http://arxiv.org/abs/1603.02041.
4. Boyan, J. A. & Littman, M. L. (2001). Exact solutions to time-dependent MDPs. In Proceedings of the 13th International Conference on Neural Information Processing Systems, Denver, CO (pp. 982–988).MIT Press.