SMDP-Based Resource Allocation for Slice Requests with Long-term Reward Maximization.
Xinli ZhouXiangming WenLuhan WangZhaoming LuWanqing GuanPublished in: ICCC Workshops (2019)
Keyphrases
- resource allocation
- reward shaping
- average reward
- semi markov decision processes
- reinforcement learning
- complex domains
- markov decision processes
- reinforcement learning algorithms
- optimal policy
- resource management
- reward function
- markov decision problems
- resource allocation problems
- long run
- state space
- objective function
- decentralized decision making
- markov chain
- resource allocation decisions
- hierarchical reinforcement learning
- optimal resource allocation
- decision making
- resource consumption
- dynamic programming
- learning agent
- policy iteration