6 papers · 1 filter
GFlowNet Foundations
Yoshua Bengio, Salem Lahlou, Tristan Deleu +3
Generative Flow Networks (GFlowNets) have been introduced as a method to sample a diverse set of candidates in an active learning context, with a training objective that makes them…
Gymnasium: A Standard Interface for Reinforcement Learning Environments
Mark Towers, Ariel Kwiatkowski, Jordan Terry +13
Reinforcement Learning (RL) is a continuously growing field that has the potential to revolutionize many areas of artificial intelligence. However, despite its promise, RL research…
Relative Trajectory Balance is equivalent to Trust-PCL
Tristan Deleu, Padideh Nouri, Yoshua Bengio +1
Recent progress in generative modeling has highlighted the importance of Reinforcement Learning (RL) for fine-tuning, with KL-regularized methods in particular proving to be highly…
Generative Flow Networks: Theory and Applications to Structure Learning
Tristan Deleu
Without any assumptions about data generation, multiple causal models may explain our observations equally well. To avoid selecting a single arbitrary model that could result in un…
Bayesian learning of Causal Structure and Mechanisms with GFlowNets and Variational Bayes
Mizu Nishikawa-Toomey, Tristan Deleu, Jithendaraa Subramanian +2
Bayesian causal structure learning aims to learn a posterior distribution over directed acyclic graphs (DAGs), and the mechanisms that define the relationship between parent and ch…
Discrete Probabilistic Inference as Control in Multi-path Environments
Tristan Deleu, Padideh Nouri, Nikolay Malkin +2
We consider the problem of sampling from a discrete and structured distribution as a sequential decision problem, where the objective is to find a stochastic policy such that objec…