Learning a Policy for Opportunistic Active Learning
This work addresses the challenge of efficient learning in interactive AI systems, but it appears incremental as it builds on prior work in opportunistic active learning.
The paper tackles the problem of improving model performance in interactive tasks by learning a policy that balances task completion with model improvement, using reinforcement learning for an object retrieval task.
Active learning identifies data points to label that are expected to be the most useful in improving a supervised model. Opportunistic active learning incorporates active learning into interactive tasks that constrain possible queries during interactions. Prior work has shown that opportunistic active learning can be used to improve grounding of natural language descriptions in an interactive object retrieval task. In this work, we use reinforcement learning for such an object retrieval task, to learn a policy that effectively trades off task completion with model improvement that would benefit future tasks.