Interval Markov Decision Processes with Continuous Action-Spaces.
Giannis DelimpaltadakisMorteza LahijanianManuel Mazo Jr.Luca LaurentiPublished in: HSCC (2023)
Keyphrases
- action space
- markov decision processes
- state space
- state and action spaces
- continuous state
- reinforcement learning
- optimal policy
- finite state
- dynamic programming
- continuous state spaces
- policy iteration
- control policies
- finite horizon
- real valued
- planning under uncertainty
- continuous action
- markov decision process
- infinite horizon
- partially observable
- function approximators
- decision processes
- average reward
- reinforcement learning algorithms
- reward function
- markov decision problems
- fixed point
- graphical models
- search algorithm