Quantitative Programming and Markov Decision Processes.
Eneia Nicolae TodoranPublished in: SYNASC (2022)
Keyphrases
- markov decision processes
- state space
- optimal policy
- finite state
- policy iteration
- reinforcement learning
- reachability analysis
- dynamic programming
- transition matrices
- planning under uncertainty
- factored mdps
- action space
- markov decision process
- decision theoretic planning
- finite horizon
- average cost
- infinite horizon
- decision processes
- reinforcement learning algorithms
- risk sensitive
- state and action spaces
- model based reinforcement learning
- partially observable
- initial state
- probabilistic planning
- decision diagrams
- decision problems
- search algorithm
- multi agent