Learning to Multi-Task by Active Sampling

By Ashutosh Kumar Jha, Parikshit Hegde, Balaraman Ravindran. 2017

40 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.

Citations in the corpus

A Survey on Multi-Task Learning (2017, background): “In [156], [157], multiple goaldirected tasks are learned in an online setup without the need for expert supervision by actively sampling harder tasks.”
Towards Continual Reinforcement Learning: A Review and Perspectives (2020, background): “There has been some limited recent work on deciding the next task to learn on in deep multi-task RL (Sharma et al., 2017), and on learning to elicit valuable information to learn from in non-stationary multi-agent settings (Shu et al.”
Multi-Task Learning with Deep Neural Networks: A Survey (2020, methodology): “(Sharma et al., 2017) proposes a method for task scheduling in multi-task RL which is based on active learning, with three different variants.”
MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale (2021, background): “…of works employ various forms of autonomous supervision to learn diverse skills, e.g. by scaling up data collection [55], sampling suitable tasks [68] or goals [51] to practice, learning a task embedding space amenable to sampling [30], or learning a dynamics model and using model-predictive…”
Revisiting Meta-Learning as Supervised Learning (2020, background): “…et al., 2018; Clavera et al., 2019), transfer and multitask learning (Ying et al., 2018; Zhang et al., 2018b), active learning (Ravi and Larochelle, 2018; Sharma et al., 2018; Bachman et al., 2017; Ravi and Larochelle, 2018; Sharma et al., 2018; Pang et al., 2018), and teaching (Fan et al., 2018).”
Prioritized Level Replay (2020, background): “Sharma et al. (2018) extend these ideas to multi-task RL, but add the additional requirement of knowing a maximum target return for each task a priori.”
How to Train Your MAML to Excel in Few-Shot Classification (2021, background): “Recent years have witnessed an abundance of new approaches on meta-learning [29, 30, 48, 61, 63, 64, 68, 77, 79, 80, 94, 98], developed in various areas including few-shot learning [70, 85, 89, 105, 107, 110, 111, 115], optimization [3, 9, 53, 108], reinforcement and imitation learning [23, 24, 31, ”
Learning Abstract Options (2018, methodology): “In our experiments on Atari we followed conventions from past work using 16 parallel asynchronous threads and entropy regularization of 0.01 on the intra-option policies [1, 9].”