Reward-based participant selection for improving federated reinforcement learning.
Woonghee LeePublished in: ICT Express (2023)
Keyphrases
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- multi agent
- optimal policy
- markov decision processes
- partially observable environments
- eligibility traces
- distributed systems
- model free
- temporal difference
- average reward
- digital libraries
- learning problems
- selection strategy
- supervised learning
- learning algorithm
- selection algorithm
- optimal control
- reward function
- state action
- multi armed bandit