Policy Gradient Methods for Reinforcement Learning with Function Approximation and Action-Dependent Baselines

Abstract

We show how an action-dependent baseline can be used by the policy gradient theorem using function approximation, originally presented with action-independent baselines by (Sutton et al. 2000).

References in corpus (1)

• A Notation for Markov Decision Processes

Cited by in corpus (5)

• The Mirage of Action-Dependent Baselines in Reinforcement Learning
• Power Allocation in Multi-User Cellular Networks: Deep Reinforcement Learning Approaches
• Learning-based Hamilton-Jacobi-Bellman Methods for Optimal Control
• Tackling Variabilities in Autonomous Driving
• Convergence of a Human-in-the-Loop Policy-Gradient Algorithm With Eligibility Trace Under Reward, Policy, and Advantage Feedback