Self Reward Design with Fine-grained Interpretability. (arXiv:2112.15034v1 [cs.LG])

Transparency and fairness issues in Deep Reinforcement Learning may stem from
the black-box nature of deep neural networks used to learn its policy, value
functions etc. This paper proposes a way to circumvent the issues through the
bottom-up design of neural networks (NN) with detailed interpretability, where
each neuron or layer has its own meaning and utility that corresponds to
humanly understandable concept. With deliberate design, we show that lavaland
problems can be solved using NN model with few parameters. …

arxiv design interpretability