FlowPG: Action-constrained Policy Gradient with Normalizing Flows.
Janaka Chathuranga BrahmanageJiajing LingAkshat KumarPublished in: NeurIPS (2023)
Keyphrases
- policy gradient
- state action
- actor critic
- parametric optimization
- reinforcement learning
- optimal control
- function approximation
- policy search
- approximation methods
- reinforcement learning algorithms
- gradient method
- model free reinforcement learning
- variance reduction
- evaluation function
- model free
- model selection
- np hard
- multi agent