Efficient Exploration in Resource-Restricted Reinforcement Learning.
Zhihai WangTaoxing PanQi ZhouJie WangPublished in: AAAI (2023)
Keyphrases
- reinforcement learning
- function approximation
- markov decision processes
- resource allocation
- resource management
- state space
- machine learning
- information retrieval
- reinforcement learning algorithms
- resource constraints
- web resources
- objective function
- model free
- temporal difference
- social networks
- stochastic approximation
- policy search
- monte carlo
- optimal policy
- learning problems
- supervised learning
- search algorithm
- multi agent
- function approximators
- temporal difference learning