Federated Q-Learning: Linear Regret Speedup with Low Communication Cost.
Zhong ZhengFengyu GaoLingzhou XueJing YangPublished in: ICLR (2024)
Keyphrases
- communication cost
- distributed data
- sensor networks
- communication overhead
- data distribution
- reinforcement learning
- learning algorithm
- lower bound
- online learning
- low bandwidth
- reduce communication cost
- cooperative
- multi agent
- network size
- processing cost
- optimal policy
- load balancing
- data analysis
- regret bounds
- data availability
- low overhead