Edmonton
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
The objective is to maximize cumulative reward byexploring the actions to discover optimal ones (having the best expectedreward),balancedwithexploitingthem.
Ease-of-Teaching and Language Structure from Emergent Communication
Some leveloflanguage structure (e.g., compositionality) has been found in the learned communication protocols.
Supervised autoencoders: Improving generalization performance with unsupervised regularizers
Lei Le, Andrew Patterson, Martha White
Neural Information Processing Systems http://nips.cc/
No-Regret Learning in Unknown Games with Correlated Payoffs
Pier Giuseppe Sessa, Ilija Bogunovic, Maryam Kamgarpour, Andreas Krause
Neural Information Processing Systems http://nips.cc/
A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation
Runzhe Yang, Xingyuan Sun, Karthik Narasimhan
Neural Information Processing Systems http://nips.cc/
A Kernel Loss for Solving the Bellman Equation
Yihao Feng, Lihong Li, Qiang Liu
Neural Information Processing Systems http://nips.cc/
CertifyingRobustnesstoProgrammableDataBiasin DecisionTrees
Datasets can be biased due to societal inequities, human biases, underrepresentation of minorities, etc.