Multi-task Learning for Continuous Control

Abstract

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. Most notably, we show that multi-task learning outperforms our baselines and alternative knowledge sharing methods.

References in corpus (3)

• Distilling the Knowledge in a Neural Network
• Distral: Robust Multitask Reinforcement Learning
• Benchmark Environments for Multitask Learning in Continuous Domains

Cited by in corpus (7)

• Distilling Policy Distillation
• MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale
• Knowledge Transfer in Multi-Task Deep Reinforcement Learning for Continuous Control
• SECANT: Self-Expert Cloning for Zero-Shot Generalization of Visual Policies
• Learning Actionable Representations from Visual Observations
• DialogAct2Vec: Towards End-to-End Dialogue Agent by Multi-Task Representation Learning
• Evolutionary Stochastic Policy Distillation