### Biologically inspired architectures for sample-efficient deep reinforcement learning. (arXiv:1911.11285v1 [cs.LG])

Deep reinforcement learning requires a heavy price in terms of sample efficiency and overparameterization in the neural networks used for function approximation. In this work, we use tensor factorization in order to learn more compact representation for reinforcement learning policies. We show empirically that in the low-data regime, it is possible to learn online policies…