Creating an agent that performs well across multiple tasks and continuously incorporates new knowledge has been a longstanding goal of research on artificial intelligence.

We theoretically prove that RIL is able to incentivize rational workers to provide high-quality labels.

Event datasets involve irregular occurrences of events over the timeline and are prevalent in numerous domains.

Neural Information Processing Systems http://nips.cc/

Existing approaches rely on various local heuristics for enforcing the acyclicity constraint.

Neural Information Processing Systems http://nips.cc/

However, the undirected setting is often insufficient: only a causal (i.e., directed) network provides

Sampling and learning these symmetric DPP's is pretty well understood. In this work, we consider a new class of DPP's, which we call signed DPP's, where we break the symmetry and allow attractive behaviors.

Remaining a gradient-based method, it is also the first Bayesian model-agnostic meta-learning method applicable to various tasks including reinforcement learning.

Hamiltonian Monte Carlo (HMC) is a widely deployed method to sample from high-dimensional distributions in Statistics and Machine learning.