Reinforcement learning on graphs: A survey
This post provides a comprehensive overview of RL and graph mining methods and generalize these methods to Graph Reinforcement Learning (GRL) as a unified formulation.
Primal Wasserstein Imitation Learning
This post introduces Primal Wasserstein Imitation Learning (PWIL) method, based on Wasserstein distance, derives a reward function offline and efficiently replicates expert behavior in MuJoCo continuous control tasks.
Characteristic Sets: Cardinality Estimation for RDF Queries
This post introduces an algorithm for rewriting in materialization-based OWL 2 RL systems, guaranteeing correctness, improving efficiency, and enabling effective parallelization, resulting in orders of magnitude reduction in reasoning times on practical datasets.
Handling owl:sameAs via Rewriting
This post introduces an algorithm for rewriting in materialization-based OWL 2 RL systems, guaranteeing correctness, improving efficiency, and enabling effective parallelization, resulting in orders of magnitude reduction in reasoning times on practical datasets.
Competitive Programming with Rust
This post introduces competitive programming with Rust and provides useful resources.