Evolution-Guided Policy Gradient in Reinforcement Learning.
Shauharda KhadkaKagan TumerPublished in: NeurIPS (2018)
Keyphrases
- policy gradient
- reinforcement learning
- actor critic
- reinforcement learning algorithms
- policy search
- function approximation
- policy gradient methods
- optimal control
- gradient method
- model free reinforcement learning
- reinforcement learning methods
- markov decision processes
- neural network
- partially observable markov decision processes
- variance reduction
- state space
- dynamic environments
- model free
- optimal policy
- temporal difference learning
- average reward
- single agent
- control problems
- approximation methods
- function approximators
- dynamic programming
- support vector
- multi agent
- control strategies