We study multi-task reinforcement learning (RL) in tabular episodic Markov decision processes (MDPs).

Skill learning offers one way of identifying these regularities by decomposing pre-collected experiences intoasequence ofskills.

Graph Structure Learning (GSL), a family of data-centric learning approaches, has garnered substantial attention in recent years. The core concept behind GSL is to jointly optimize the graph structure and the corresponding GNN models.

Experimental results show that vanilla OSOA can save significant time versus training bespokemodels and space versus using one model for all targets.

Second, common entropy can be used to improve constraint-based methods such as PC or FCI algorithms in the small-sample regime,wherethesemethods areknowntostruggle.