Solving nonstationary Markov decision processes via contextual decomposition: A military air battle management application.
Joseph M. Liles IVMatthew J. RobbinsBrian J. LundayPublished in: Expert Syst. Appl. (2023)
Keyphrases
- markov decision processes
- non stationary
- finite horizon
- transition matrices
- reinforcement learning
- semi markov decision processes
- optimal policy
- dynamic programming
- random fields
- finite state
- reachability analysis
- planning under uncertainty
- average cost
- stochastic shortest path
- policy iteration
- state space
- decision theoretic planning
- factored mdps
- infinite horizon
- average reward
- reinforcement learning algorithms
- state and action spaces
- model based reinforcement learning
- multi agent
- partially observable
- action sets
- real time dynamic programming
- data mining