Edmonton
Multi-view Matrix Factorization for Linear Dynamical System Estimation
Mahdi Karami, Martha White, Dale Schuurmans, Csaba Szepesvari
Maximum likelihood for LDS estimation, on the other hand, has several advantages.
Actor-Critic Policy Optimization in Partially Observable Multiagent Environments
Optimization of parameterized policies for reinforcement learning (RL) is an important and challenging problem in artificial intelligence.
Differentially Private Contextual Linear Bandits
Though the context is chosen arbitrarily or adversarially, the reward is assumed to be a stochastic function of a feature vector that encodes the context and selected action. Our goal is to devise private learners for the contextual linear bandit problem.
Supervised autoencoders: Improving generalization performance with unsupervised regularizers
Lei Le, Andrew Patterson, Martha White
Generalization performance is a central goal in machine learning, with explicit generalization strategies needed when training over-parametrized models, like large neural networks. There is growing interest in using multiple, potentially auxiliary tasks, as one strategy towards this goal.
Distributional Reinforcement Learning with Regularized Wasserstein Loss Ke Sun
Empirically, we show that SinkhornDRL consistently outperforms or matches existing algorithms on the Atari games suite and particularly stands out in the multi-dimensional reward setting.
Toward Conditional Distribution Calibration in Survival Prediction Shi-ang Qi1, Y akun Y u
This method effectively improves the model's marginal and conditional calibration,