Adaptive Decision-Making in Non-Stationary Markov Decision Processes.
Baiting LuoPublished in: AAMAS (2024)
Keyphrases
- non stationary
- markov decision processes
- adaptive algorithms
- decision making
- optimal policy
- decision processes
- state space
- finite state
- dynamic programming
- transition matrices
- policy iteration
- reinforcement learning
- finite horizon
- reachability analysis
- partially observable
- decision theoretic planning
- reinforcement learning algorithms
- decision makers
- factored mdps
- markov decision process
- risk sensitive
- average cost
- random fields
- model based reinforcement learning
- average reward
- infinite horizon
- empirical mode decomposition
- decision problems
- planning under uncertainty
- reward function
- change point detection
- action sets
- multistage
- semi markov decision processes
- machine learning