Imperfect game play with counterfactual regret minimisation https://www.cs.cmu.edu/~noamb/papers/19-Science-Superhuman.pdf
Representation learning is concerned with training machine learning algorithms to learn useful representations, e.g. those that are interpretable, have latent features, or can be used for transfer learning.
Continual Unsupervised Representation Learning http://papers.nips.cc/paper/8981-continual-unsupervised-representation-learning.pdf
Felix Hill - Grounded Language Learning in a Simulated 3D World https://arxiv.org/pdf/1706.06551.pdf
“I reject the contention that an important theoretical difference exists between formal and natural languages.” (Montague, 1970)