Probabilistic Preference Planning Problem for Markov Decision Processes.
Meilun LiAndrea TurriniErnst Moritz HahnZhikun SheLijun ZhangPublished in: IEEE Trans. Software Eng. (2022)
Keyphrases
- markov decision processes
- probabilistic planning
- planning under uncertainty
- macro actions
- decision theoretic planning
- partially observable
- state space
- finite state
- policy iteration
- optimal policy
- planning problems
- dynamic programming
- reinforcement learning
- reachability analysis
- heuristic search
- transition matrices
- decision processes
- probabilistic model
- finite horizon
- average cost
- partially observable markov decision processes
- factored mdps
- bayesian networks
- semi markov decision processes
- markov chain
- markov decision problems
- average reward
- model based reinforcement learning
- generative model
- decision theoretic
- markov decision process
- infinite horizon
- reinforcement learning algorithms
- ai planning
- multistage
- reward function
- search algorithm