Search Results for author: Sobhan Mohammadpour

Found 2 papers, 0 papers with code

Maximum entropy GFlowNets with soft Q-learning

no code implementations21 Dec 2023 Sobhan Mohammadpour, Emmanuel Bengio, Emma Frejinger, Pierre-Luc Bacon

Generative Flow Networks (GFNs) have emerged as a powerful tool for sampling discrete objects from unnormalized distributions, offering a scalable alternative to Markov Chain Monte Carlo (MCMC) methods.

Q-Learning Reinforcement Learning (RL)

Arc travel time and path choice model estimation subsumed

no code implementations25 Oct 2022 Sobhan Mohammadpour, Emma Frejinger

We propose a method for maximum likelihood estimation of path choice model parameters and arc travel time using data of different levels of granularity.

Cannot find the paper you are looking for? You can Submit a new open access paper.