Act as You Learn: Adaptive Decision-Making in Non-Stationary Markov Decision Processes.
Baiting LuoYunuo ZhangAbhishek DubeyAyan MukhopadhyayPublished in: AAMAS (2024)
Keyphrases
- non stationary
- markov decision processes
- adaptive algorithms
- decision making
- finite state
- state space
- finite horizon
- decision processes
- policy iteration
- reinforcement learning
- transition matrices
- optimal policy
- decision theoretic planning
- planning under uncertainty
- dynamic programming
- reachability analysis
- markov decision process
- decision makers
- risk sensitive
- action space
- reinforcement learning algorithms
- factored mdps
- action sets
- real time dynamic programming
- model based reinforcement learning
- empirical mode decomposition
- average cost
- infinite horizon
- average reward
- reward function
- change point detection
- supply chain
- partially observable
- state abstraction
- state and action spaces
- decision theory
- least squares
- machine learning
- data mining