On Divergence Measures for Training GFlowNets
–Neural Information Processing Systems
In reinforcement learning (RL), a recurring goal is to find a diverse set of high-valued state-action trajectories according to a reward function.
Neural Information Processing Systems
Oct-10-2025, 08:52:08 GMT
- Country:
- Asia > Middle East
- Jordan (0.04)
- Europe > United Kingdom
- England
- Cambridgeshire > Cambridge (0.04)
- Oxfordshire > Oxford (0.04)
- England
- North America > United States
- California (0.04)
- South America > Brazil
- Rio de Janeiro > Rio de Janeiro (0.04)
- São Paulo (0.04)
- Asia > Middle East
- Genre:
- Research Report
- Experimental Study (1.00)
- New Finding (0.92)
- Research Report
- Industry:
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning
- Learning Graphical Models > Directed Networks
- Bayesian Learning (0.46)
- Neural Networks > Deep Learning (0.46)
- Reinforcement Learning (0.66)
- Statistical Learning (1.00)
- Learning Graphical Models > Directed Networks
- Natural Language (1.00)
- Representation & Reasoning
- Optimization (0.68)
- Uncertainty > Bayesian Inference (0.68)
- Machine Learning
- Information Technology > Artificial Intelligence