In a single-agent setting, IL was shown to be done efficiently via an inverse soft-Q learning process.

Bayes' rule naturally allows for inference refinement in a streaming fashion, without the need to recompute posteriors from scratch whenever new data arrives.

The paper proves generalization results for a class of stochastic learning algorithms.

In this direction, we provide a general bound under a new model-dependent assumption from which we obtain bounds based on parameter norms and log-Sobolev inequalities.

Work done as a visiting student at MIT. 38th Conference on Neural Information Processing Systems (NeurIPS 2024).

Some existing works have proposed score matching estimators for point processes.