Learning Robust Policies for Uncertain Parametric Markov Decision Processes.
Luke RickardAlessandro AbateKostas MargellosPublished in: CoRR (2023)
Keyphrases
- markov decision processes
- reinforcement learning
- optimal policy
- model based reinforcement learning
- state space
- macro actions
- learning algorithm
- dynamic programming
- learning tasks
- partially observable
- markov decision process
- stochastic games
- decision making
- decision theoretic planning
- state abstraction
- continuous state spaces
- decision processes
- finite horizon
- policy iteration
- average cost
- planning under uncertainty
- partially observable markov decision processes
- state and action spaces
- reward function
- decision problems