Deciding What Is Good-For-MDPs.
Sven ScheweQiyi TangTansholpan ZhanabekovaPublished in: CONCUR (2023)
Keyphrases
- markov decision processes
- reinforcement learning
- state space
- factored mdps
- finite horizon
- finite state
- markov decision process
- semi markov decision processes
- optimal policy
- decision theoretic planning
- partially observable
- initial state
- planning under uncertainty
- real time dynamic programming
- model based reinforcement learning
- dynamic programming
- decision diagrams
- markov decision problems
- making decisions
- average cost
- average reward
- decision making
- factored markov decision processes