Stability-constrained Markov Decision Processes using MPC.
Mario ZanonSébastien GrosMichele PalladinoPublished in: Autom. (2022)
Keyphrases
- markov decision processes
- optimal policy
- finite state
- dynamic programming
- reinforcement learning
- transition matrices
- state space
- reachability analysis
- policy iteration
- decision theoretic planning
- average cost
- decision processes
- finite horizon
- infinite horizon
- factored mdps
- model based reinforcement learning
- reinforcement learning algorithms
- average reward
- action space
- risk sensitive
- planning under uncertainty
- partially observable
- decision diagrams
- action sets
- semi markov decision processes
- markov decision process
- interval estimation