Fetching the paper…

Reading the bibliography…

2018

Multi-task Learning for Continuous Control

Arora, Himani, Kumar, Rajath, Krone, Jason et al.

Original
PDF
Post on X

Understand

Reliable and effective multi-task learning is a prerequisite for the development of robotic agents that can quickly learn to accomplish related, everyday tasks.

However, in the reinforcement learning domain, multi-task learning has not exhibited the same level of success as in other domains, such as computer vision.
In addition, most reinforcement learning research on multi-task learning has been focused on discrete action spaces, which are not used for robotic control in the real-world.
In this work, we apply multi-task learning methods to continuous action spaces and benchmark their performance on a series of simulated continuous control tasks.

Multi-task Learning for Continuous Control · Around

Built on

Function optimization using connectionist reinforcement learning algorithms
Williams, Ronald J and Peng, Jing · 1991
Earlier work this paper cites.
Model compression
Bucila, Cristian, Caruana, Rich, and Niculescu-Mizil, Alexandru · 2006
Earlier work this paper cites.
Distilling the knowledge in a neural network
Hinton, G., Vinyals, O., and Dean, J · 2014
Earlier work this paper cites.

Similar

Asynchronous methods for deep reinforcement learning
Mnih, Volodymyr, Badia, Adrià Puigdomènech, Mirza, Mehdi, Graves, Alex, Harley, Tim, Lillicrap, Timothy P., Silver, David, and Kavukcuoglu, Koray · 2016
Cited alongside, same era.
Actor-mimic deep multitask and transfer reinforcement learning
Parisotto, Emilio, Ba, Jimmy, and Salakhutdinov, Ruslan · 2016
Cited alongside, same era.
Policy distilation
Original
Rusu, Andrei A., Colmenarejo, Sergio Gomez, Gulcehr, Caglar, Desjardins, Guillaume, Kirkpatrick, James, Pascanu, Razvan, Mnih, Volodymyr, Kavukcuoglu, Koray, and Hadsell, Raia
Cited in the paper.
Progressive neural networks
Original
Rusu, Andrei A., Rabinowitz, Neil C., Desjardins, Guillaume, Soyer, Hubert, Kirkpatrick, James, Kavukcuoglu, Koray, Pascanu, Razvan, and Hadsell, Raia
Cited in the paper.

Then

Benchmark environments for multitask learning in continuous domains
Original
Henderson, Peter, Chang, Wei-Di, Shkurti, Florian, Hansen, Johanna, Meger, David, and Dudek, Gregory · 2017
Later among the works it cites.
Distral: Robust multitask reinforcement learning
Original
Teh, Yee Whye, Bapst, Victor, Czarnecki, Wojciech Marian, Quan, John, Kirkpatrick, James, Hadsell, Raia, Heess, Nicolas, and Pascanu, Razvan · 2017
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…