A unified view of configurable Markov Decision Processes: Solution concepts, value functions, and operators.
Alberto Maria MetelliPublished in: Intelligenza Artificiale (2022)
Keyphrases
- markov decision processes
- solution concepts
- decision diagrams
- optimal policy
- state space
- transition matrices
- game theoretic
- finite state
- coalition formation
- reinforcement learning
- dynamic programming
- policy iteration
- decision theoretic planning
- game theory
- reinforcement learning algorithms
- nash equilibrium
- markov decision process
- average reward
- von neumann
- infinite horizon
- decision problems
- nash equilibria
- open questions
- reward function
- learning algorithm
- utility function
- multi agent systems
- real time dynamic programming