Policy Gradient using Weak Derivatives for Reinforcement Learning.
Sujay BhattAlec KoppelVikram KrishnamurthyPublished in: CoRR (2020)
Keyphrases
- policy gradient
- reinforcement learning
- actor critic
- reinforcement learning algorithms
- function approximation
- policy search
- optimal control
- model free reinforcement learning
- policy gradient methods
- gradient method
- state space
- model free
- average reward
- reinforcement learning methods
- approximation methods
- temporal difference
- state action
- variance reduction
- function approximators
- partially observable markov decision processes
- approximate dynamic programming
- markov decision processes
- monte carlo
- control system
- reinforcement learning problems
- support vector
- machine learning