Act as You Learn: Adaptive Decision-Making in Non-Stationary Markov Decision Processes.
Baiting LuoYunuo ZhangAbhishek DubeyAyan MukhopadhyayPublished in: CoRR (2024)
Keyphrases
- non stationary
- markov decision processes
- adaptive algorithms
- decision making
- state space
- finite state
- transition matrices
- decision processes
- optimal policy
- finite horizon
- policy iteration
- dynamic programming
- reinforcement learning algorithms
- reinforcement learning
- decision theoretic planning
- decision makers
- reachability analysis
- infinite horizon
- average cost
- average reward
- model based reinforcement learning
- partially observable
- planning under uncertainty
- markov decision process
- random fields
- data mining
- supply chain
- change point detection
- factored mdps
- risk sensitive
- action space
- multistage
- discounted reward
- empirical mode decomposition
- linear programming
- decision process
- reward function
- optimal solution
- image sequences
- stochastic shortest path