Learning Graphical Models
Constructing Deep Neural Networks by Bayesian Network Structure Learning
Raanan Y. Rohekar, Shami Nisimov, Yaniv Gurwicz, Guy Koren, Gal Novik
We introduce a principled approach for unsupervised structure learning of deep neural networks.
RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorization
Multi-agent systems are characterized by environmental uncertainty, varying policies of agents, and partial observability, which result in significant risks.
Beyond Confidence Regions: Tight Bayesian Ambiguity Sets for Robust MDPs
Marek Petrik, Reazul Hasan Russel
Neural Information Processing Systems http://nips.cc/
Expressive power of tensor-network factorizations for probabilistic modeling
Ivan Glasser, Ryan Sweke, Nicola Pancotti, Jens Eisert, Ignacio Cirac
Whenusedtomodelprobability distributions, theyexhibit tractable likelihoods and admit efficient learning algorithms.
Implicit Reparameterization Gradients
Mikhail Figurnov, Shakir Mohamed, Andriy Mnih
Neural Information Processing Systems http://nips.cc/
9023effe3c16b0477df9b93e26d57e2c-Paper.pdf
This simple intuition makes Bayesian methods appealing approaches for transfer in RL, and many previous works have been proposed in this direction.