Online Resource Allocation in Episodic Markov Decision Processes.
Duksang LeeDabeen LeePublished in: CoRR (2023)
Keyphrases
- resource allocation
- markov decision processes
- optimal policy
- state space
- transition matrices
- finite state
- reinforcement learning
- resource management
- dynamic programming
- partially observable
- resource allocation problems
- reachability analysis
- decision theoretic planning
- policy iteration
- optimal resource allocation
- allocation problems
- markov decision process
- average reward
- planning under uncertainty
- reinforcement learning algorithms
- average cost
- finite horizon
- action space
- infinite horizon
- resource allocation decisions
- game theory
- model based reinforcement learning
- cooperative
- action sets
- grid environment
- decision problems
- resource allocation and scheduling