Context-Aware Policy Reuse
By Siyuan Li, Fangda Gu, Guangxiang Zhu, Chongjie Zhang. 2018
41 citations recorded by the source corpus.
Transfer learning can greatly speed up reinforcement learning for a new task by leveraging policies of relevant tasks. Existing works of policy reuse either focus on selecting a single best source policy for reuse without considering contexts, or fail to guarantee learning an optimal policy for a target task. To improve transfer efficiency and guarantee optimality, we develop a novel policy reuse method, called Context-Aware Policy reuSe (CAPS), that enables multi-policy reuse. Our method learns when and which source policy is best for reuse, as well as when to terminate its reuse. CAPS provides theoretical guarantees in convergence and optimality for both source policy selection and target task learning. Empirical results on a grid-based navigation domain and the Pygame Learning Environment demonstrate that CAPS significantly outperforms other state-of-the-art policy reuse methods.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
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 Vision and Pattern Recognition
Citations in the corpus
- Towards Continual Reinforcement Learning: A Review and Perspectives (2020, background): “Changepoint Detection: As discussed previously, one core issue in addressing settings with evolving task states is being able to detect change points or boundaries between significant switches without an oracle as in (Da Silva et al., 2006; Rosman and Ramamoorthy, 2012; Hadoux et al., 2014b; Padakan”