Adaptive Auxiliary Task Weighting for Reinforcement Learning

By Xingyu Lin, Harjatin Singh Baweja, George A. Kantor, David Held. 2019

133 citations recorded by the source corpus.

How researchers see this paper

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

1. Qiang Yang
2. Yu Zhang
3. Sergey Levine
4. Tianhe Yu
5. Graham Neubig
6. Dacheng Tao
7. Chelsea Finn
8. Yoshua Bengio

Citations in the corpus

• A Survey on Multi-Task Learning (2017, methodology): “In [160], an online learning algorithm is proposed to dynamically combine different auxiliary tasks which pro-”
• Efficiently Identifying Task Groupings for Multi-Task Learning (2021, methodology): “This approach has been used extensively in the meta-learning [16, 42, 7, 17, 29], optimization [41, 21, 55, 23, 24], and recently auxiliary task learning domains [34].”
• Auxiliary Tasks Speed Up Learning PointGoal Navigation (2020, unknown): “In contrast to prior work, which focus on simpler and non-photorealistic environments [17, 19, 20, 21, 22], we focus on visually complex, photorealistic environments from the Gibson 3D scans [30].”
• Model-augmented Prioritized Experience Replay (2022, methodology): “…for improving the exploration (Pathak et al., 2017; Shelhamer et al., 2016) or to enhance representation learning for pixel-based observations (Lin et al., 2019; Agarwal et al., 2021; Stooke et al., 2021; Lee et al., 2020b; Schrittwieser et al., 2020; Hessel et al., 2021; Hafner et al.,…”
• Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative (2021, methodology): “Our analysis above is similar to that of Lin et al. (2019) with one key difference: we learn a weighting for the main task w∗ too.”
• Multi-Task Reinforcement Learning with Soft Modularization (2020, background): “Researchers also propose to explicitly model the similarity between gradients from different tasks [44, 4, 15, 19, 35, 6, 42, 12].”