Continuous MDP Homomorphisms and Homomorphic Policy Gradient.
Sahand Rezaei-ShoshtariRosie ZhaoPrakash PanangadenDavid MegerDoina PrecupPublished in: CoRR (2022)
Keyphrases
- policy gradient
- reinforcement learning
- average reward
- markov decision processes
- policy search
- partially observable markov decision processes
- reinforcement learning algorithms
- actor critic
- action space
- state action
- optimal policy
- utility function
- function approximation
- model free reinforcement learning
- finite state
- state space
- markov decision process
- approximation methods
- optimal control
- gradient method
- reward function
- variance reduction
- decision problems
- linear program
- search algorithm