Weakly-Supervised Reinforcement Learning for Controllable Behavior

04/06/2020
by   Lisa Lee, et al.
11

Reinforcement learning (RL) is a powerful framework for learning to take actions to solve tasks. However, in many settings, an agent must winnow down the inconceivably large space of all possible tasks to the single task that it is currently being asked to solve. Can we instead constrain the space of tasks to those that are semantically meaningful? In this work, we introduce a framework for using weak supervision to automatically disentangle this semantically meaningful subspace of tasks from the enormous space of nonsensical "chaff" tasks. We show that this learned subspace enables efficient exploration and provides a representation that captures distance between states. On a variety of challenging, vision-based continuous control problems, our approach leads to substantial performance gains, particularly as the complexity of the environment grows.

READ FULL TEXT

page 3

page 6

page 8

page 14

research
06/11/2021

Offline Reinforcement Learning as Anti-Exploration

Offline Reinforcement Learning (RL) aims at learning an optimal control ...
research
04/05/2022

Jump-Start Reinforcement Learning

Reinforcement learning (RL) provides a theoretical framework for continu...
research
10/22/2020

Batch Exploration with Examples for Scalable Robotic Reinforcement Learning

Learning from diverse offline datasets is a promising path towards learn...
research
01/13/2022

Weakly Supervised Scene Text Detection using Deep Reinforcement Learning

The challenging field of scene text detection requires complex data anno...
research
10/02/2021

Seeking Visual Discomfort: Curiosity-driven Representations for Reinforcement Learning

Vision-based reinforcement learning (RL) is a promising approach to solv...
research
11/05/2018

Contingency-Aware Exploration in Reinforcement Learning

This paper investigates whether learning contingency-awareness and contr...
research
09/23/2019

Why Does Hierarchy (Sometimes) Work So Well in Reinforcement Learning?

Hierarchical reinforcement learning has demonstrated significant success...

Please sign up or login with your details

Forgot password? Click here to reset