Learning robust policies for uncertain parametric Markov decision processes.
Luke RickardAlessandro AbateKostas MargellosPublished in: L4DC (2024)
Keyphrases
- markov decision processes
- reinforcement learning
- optimal policy
- macro actions
- state space
- learning algorithm
- model based reinforcement learning
- reward function
- dynamic programming
- partially observable
- markov decision process
- finite horizon
- decision processes
- transition matrices
- action sets
- decentralized control
- reinforcement learning algorithms
- finite state
- supervised learning
- state abstraction
- factored mdps
- hierarchical reinforcement learning
- decision making