Learning from Human Feedback: Challenges for Real-World Reinforcement Learning in NLP

by   Julia Kreutzer, et al.

Large volumes of interaction logs can be collected from NLP systems that are deployed in the real world. How can this wealth of information be leveraged? Using such interaction logs in an offline reinforcement learning (RL) setting is a promising approach. However, due to the nature of NLP tasks and the constraints of production systems, a series of challenges arise. We present a concise overview of these challenges and discuss possible solutions.


page 1

page 2

page 3

page 4


Challenges of Real-World Reinforcement Learning

Reinforcement learning (RL) has proven its worth in a series of artifici...

Interviewer-Candidate Role Play: Towards Developing Real-World NLP Systems

Standard NLP tasks do not incorporate several common real-world scenario...

An empirical investigation of the challenges of real-world reinforcement learning

Reinforcement learning (RL) has proven its worth in a series of artifici...

Personalization for Web-based Services using Offline Reinforcement Learning

Large-scale Web-based services present opportunities for improving UI po...

Using Conformity to Probe Interaction Challenges in XR Collaboration

The concept of a conformity spectrum is introduced to describe the degre...

Batch-Constrained Distributional Reinforcement Learning for Session-based Recommendation

Most of the existing deep reinforcement learning (RL) approaches for ses...

Offline-Online Reinforcement Learning for Energy Pricing in Office Demand Response: Lowering Energy and Data Costs

Our team is proposing to run a full-scale energy demand response experim...