Policy Gradient using Weak Derivatives for Reinforcement Learning.
Sujay BhattAlec KoppelVikram KrishnamurthyPublished in: CDC (2019)
Keyphrases
- policy gradient
- reinforcement learning
- actor critic
- function approximation
- reinforcement learning algorithms
- policy search
- optimal control
- gradient method
- policy gradient methods
- model free reinforcement learning
- state space
- variance reduction
- model free
- learning algorithm
- multi agent
- optimal policy
- average reward
- approximation methods
- function approximators
- partially observable markov decision processes
- single agent
- markov decision processes
- temporal difference learning
- reinforcement learning methods
- approximate dynamic programming
- temporal difference
- dynamical systems
- state action
- control problems
- sufficient conditions
- reward function
- radial basis function