Parallel Reinforcement Learning

By Matt Kretchmar. 2002

Subfields: Reinforcement Learning, ML Systems & Hardware

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Reinforcement Learning

1. Simon Schmitt
2. Matteo Hessel
3. Karen Simonyan
4. Qiang Yang
5. Jim Duggan
6. Yang Liu
7. Enda Barrett
8. Enda Howley

In ML Systems & Hardware

1. Tianjian Chen
2. Qiang Yang
3. Yang Liu

Citations in the corpus

• Off-Policy Actor-Critic with Shared Experience Replay (2019, background): “Sharing experience permits the agents to benefit from parallel exploration (Kretchmar, 2002) (Figures 1 and 3).”
• Applying reinforcement learning towards automating resource allocation and application scalability in the cloud (2013, background): “Previous work by Kretchmar [33] has demonstrated the convergence speedups made possible by applying a parallel reinforcement learning approach in a general setting.”
• Parallel reinforcement learning with linear function approximation (2007, unknown): “While there have been preliminary analyses [3, 7] demonstrating the promise of a parallel approach to RL, the cost of inter-agent communication has usually been ignored.”
• Federated Transfer Reinforcement Learning for Autonomous Driving (2019, background): “[13] presents two real-life FRL examples for privacy-preserving issues both in manufactory industry and medical treatment systems.”