mlsanityData to 14 Oct 2026

Active Reinforcement Learning: Observing Rewards at a Cost

arXiv 2011.06709 ↗First posted 13 Nov 2020cs.LG cs.AI stat.MLcited by 20

Not on the map. Why?

Abstract (arXiv)

Active reinforcement learning (ARL) is a variant on reinforcement learning where the agent does not observe the reward unless it chooses to pay a query cost c > 0. The central question of ARL is how to quantify the long-term value of reward information. Even in multi-armed bandits, computing the value of this information is intractable and we have to rely on heuristics. We propose and evaluate several heuristic approaches for ARL in multi-armed bandits and (tabular) Markov decision processes, and discuss and illustrate some challenging aspects of the ARL problem.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). First posted on arXiv 13 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 0; 2023: 4; 2024: 4; 2025: 7; 2026: 2.

20 papers.

Sort:

By area:

  1. 2021Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challengescited by 50
  2. 2024Reinforcement Learning from Human Feedback with Active Queriescited by 43
  3. 2021Active Offline Policy Selectioncited by 26
  4. 2024Monitored Markov Decision Processescited by 10
  5. 2023Embodied Active Learning of Relational State Abstractions for Bilevel Planningcited by 8
  6. 2024Batch Active Learning of Reward Functions from Human Preferencescited by 8
  7. 2024Beyond Optimism: Exploration With Partially Observable Rewardscited by 6
  8. 2025Active Advantage-Aligned Online Reinforcement Learning with Offline Datacited by 5
  9. 2021Scientific Discovery and the Cost of Measurement -- Balancing Information and Cost in Reinforcement Learningcited by 4
  10. 2023Active Learning for Video Classification with Frame Level Queriescited by 2
  11. 2023Learning Computational Efficient Bots with Costly Featurescited by 2
  12. 2025Efficient Reinforcement Learning from Human Feedback via Bayesian Preference Inferencecited by 2
8 more
  1. 2025Model-Based Exploration in Monitored Markov Decision Processescited by 1
  2. 2025Active Measuring in Reinforcement Learning With Delayed Negative Effectscited by 1
  3. 2023Active Vision Reinforcement Learning under Limited Visual Observabilitycited by 0
  4. 2025Which Rewards Matter? Reward Selection for Reinforcement Learning under Limited Feedbackcited by 0
  5. 2025Optimizing Algorithms for Mobile Health Interventions with Active Querying Optimizationcited by 0
  6. 2025Learning to Wait: Synchronizing Agents with the Physical Worldcited by 0
  7. 2026Remote Action Generation: Remote Control with Minimal Communicationcited by 0
  8. 2026GoStop: Reinforcement Learning for Adaptive Temporal Aggregation in Event-Based Feature Trackingcited by 0