On-Policy Reinforcement Learning via Ensemble Gaussian Processes with Application to Resource Allocation.
Konstantinos D. PolyzosQin LuAlireza SadeghiGeorgios B. GiannakisPublished in: ACSCC (2021)
Keyphrases
- resource allocation
- gaussian processes
- reinforcement learning
- optimal resource allocation
- gaussian process
- optimal policy
- gaussian process regression
- resource allocation problems
- scarce resources
- markov decision processes
- multi task
- hyperparameters
- state space
- gaussian process models
- allocation problems
- multi agent
- machine learning