Goto

Collaborating Authors

 Learning Graphical Models

927962d8866377a07ee3150d2d691319-Paper-Conference.pdf

91f9fb16b5679115a777ade51af87e48-Supplemental-Conference.pdf

Causal Discovery in Semi-Stationary Time Series

Neural Information Processing Systems

Discovering causal relations from observational time series without making the stationary assumption is a significant challenge.

Pairwise Causality Guided Transformers for Event Sequences

Neural Information Processing Systems

Such statements embed the notion of pairwise causality and can be better paraphrased as'occurrences of event type Z

Efficient RL with Impaired Observability: Learning to Act with Delayed and Missing State Observations

Neural Information Processing Systems

In Reinforcement Learning (RL), an agent engages with an environment in a sequential manner.

9156b0f6dfa9bbd18c79cc459ef5d61c-Paper-Conference.pdf

Active Observing in Continuous-time Control

Neural Information Processing Systems

The decision-maker's observing policy must be timely

Active Observing in Continuous-time Control

Neural Information Processing Systems

The decision-maker's observing policy must be timely

8ec61d4084443d29c9e47ac60f9aea31-Paper-Conference.pdf

Beyond Black-Box Advice: Learning-Augmented Algorithms for MDPs with Q-Value Predictions

Neural Information Processing Systems

A notable example that motivates our work is the problem of minimizing costs (or maximizing rewards) in a single-trajectory Markov Decision Process (MDP).