Generalized Proximal Policy Optimization with Sample Reuse
By James Queeney, Ioannis Ch. Paschalidis, Christos G. Cassandras. 2021
73 citations recorded by the source corpus.
In real-world decision making tasks, it is critical for data-driven reinforcement learning methods to be both stable and sample efficient. On-policy methods typically generate reliable policy improvement throughout training, while off-policy methods make more efficient use of data through sample reuse. In this work, we combine the theoretically supported stability benefits of on-policy algorithms with the sample efficiency of off-policy algorithms. We develop policy improvement guarantees that are suitable for the off-policy setting, and connect these bounds to the clipping mechanism used in Proximal Policy Optimization. This motivates an off-policy version of the popular algorithm that we call Generalized Proximal Policy Optimization with Sample Reuse. We demonstrate both theoretically and empirically that our algorithm delivers improved performance by effectively balancing the competing goals of stability and sample efficiency.
Subfields: Artificial Intelligence, Computer Networks and Communications
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Matthew Riemer
- Irina Rish
- Khimya Khetarpal
- Doina Precup
- Sergey Levine
- Joelle Pineau
- Eric Eaton
- Chelsea Finn
In Computer Networks and Communications
Citations in the corpus
- Towards Continual Reinforcement Learning: A Review and Perspectives (2020, background): “…Hwang, 2021; Henning, Cervera, D’Angelo, Von Oswald, Traber, Ehret, Kobayashi, Grewe, and Sacramento, 2021; Liu, Xue, Pang, Jiang, Xu, and Yu, 2021b; Queeney, Paschalidis, and Cassandras, 2021; Chandak, Niekum, da Silva, Learned-Miller, Brunskill, and Thomas, 2021; Lampinen, Chan, Banino, and…”