Addressing Stale Gradients in Scalable Federated Deep Reinforcement Learning.
Justin StanleyAli JannesariPublished in: SC Workshops (2023)
Keyphrases
- reinforcement learning
- function approximation
- state space
- reinforcement learning algorithms
- digital libraries
- web scale
- machine learning
- temporal difference
- model free
- reinforcement learning methods
- radial basis function
- temporal difference learning
- learning agent
- memory efficient
- action selection
- markov decision processes
- lightweight
- distributed systems
- active learning
- learning process
- e learning