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