Learning Graphical Models
Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck
Maximilian Igl, Kamil Ciosek, Yingzhen Li, Sebastian Tschiatschek, Cheng Zhang, Sam Devlin, Katja Hofmann
Neural Information Processing Systems http://nips.cc/
D-VAE: A Variational Autoencoder for Directed Acyclic Graphs
Muhan Zhang, Shali Jiang, Zhicheng Cui, Roman Garnett, Yixin Chen
Neural Information Processing Systems http://nips.cc/
Structure Learning with Side Information: Sample Complexity
Neural Information Processing Systems http://nips.cc/
A neurally plausible model learns successor representations in partially observable environments
However, it is not clear how such representations might be learned and computed in partially observed, noisy environments. Here, we introduce a neurally plausible model using distributional successor features, which builds on the distributed distributional code for the representation and computation of uncertainty, and which allows for efficient value function computation in partially observed environments via the successor representation.
Exploration Bonus for Regret Minimization in Discrete and Continuous Average Reward MDPs
Jian QIAN, Ronan Fruit, Matteo Pirotta, Alessandro Lazaric
The exploration bonus is an effective approach to manage the exploration-exploitation trade-off in Markov Decision Processes (MDPs).
Amortized Bethe Free Energy Minimization for Learning MRFs
We propose to learn deep undirected graphical models (i.e., MRFs) with a non-ELBO objective for which we can calculate exact gradients.
The Functional Neural Process
Christos Louizos, Xiahan Shi, Klamer Schutte, Max Welling
Neural Information Processing Systems http://nips.cc/
Identifying Causal Effects via Context-specific Independence Relations
Santtu Tikka, Antti Hyttinen, Juha Karvanen
Neural Information Processing Systems http://nips.cc/
Scalable Structure Learning of Continuous-Time Bayesian Networks from Incomplete Data
Dominik Linzner, Michael Schmidt, Heinz Koeppl
The CIMs are the generators of the dynamics of a CTBN.
Modelling heterogeneous distributions with an Uncountable Mixture of Asymmetric Laplacians
Axel Brando, Jose A. Rodriguez, Jordi Vitria, Alberto Rubio Muñoz
On the other hand, another source of uncertainty is "inevitable variability in the response variable", i.e. when the variable to predict exhibits randomness,