Federated Reinforcement Learning: Linear Speedup Under Markovian Sampling.
Sajad KhodadadianPranay SharmaGauri JoshiSiva Theja MaguluriPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- multi agent
- orders of magnitude
- function approximators
- function approximation
- point processes
- action selection
- sample size
- optimal policy
- distributed systems
- closed form
- supervised learning
- random sampling
- model free
- digital libraries
- learning algorithm
- transfer learning
- dynamic programming
- reinforcement learning algorithms
- sampling algorithm