Markov Decision Processes with Rewards.
Maximilian SchäffelerMohammad AbdulazizPublished in: Arch. Formal Proofs (2021)
Keyphrases
- markov decision processes
- reinforcement learning
- state space
- optimal policy
- finite state
- decision theoretic planning
- policy iteration
- sequential decision making under uncertainty
- reachability analysis
- average reward
- reward function
- reinforcement learning algorithms
- factored mdps
- dynamic programming
- decision processes
- discounted reward
- action space
- finite horizon
- infinite horizon
- transition matrices
- model based reinforcement learning
- planning under uncertainty
- action sets
- markov decision process
- semi markov decision processes
- state abstraction
- expected reward
- partially observable
- search algorithm
- data mining
- total reward
- decision diagrams
- least squares
- heuristic search
- average cost