FlowPG: Action-constrained Policy Gradient with Normalizing Flows
–Neural Information Processing Systems
Second, learning the flow model requires sampling from the feasible action space, which is also challenging.
Neural Information Processing Systems
Feb-10-2026, 21:37:40 GMT
- Genre:
- Research Report (0.68)
- Technology:
- Information Technology > Artificial Intelligence
- Representation & Reasoning (1.00)
- Robots (0.94)
- Machine Learning
- Neural Networks (1.00)
- Statistical Learning (0.93)
- Reinforcement Learning (0.70)
- Information Technology > Artificial Intelligence