MétaCan
Menu
Back to cohort
Record W4391399751 · doi:10.1613/jair.1.15348

Human-in-the-Loop Reinforcement Learning: A Survey and Position on Requirements, Challenges, and Opportunities

2024· article· en· W4391399751 on OpenAlexafffund
Carl Orge Retzlaff, Srijita Das, Christabel Wayllace, Payam Mousavi, Mohammad Afshari, Tianpei Yang, Anna Saranti, Alessa Angerschmid, Matthew E. Taylor, Andreas Holzinger

Bibliographic record

VenueJournal of Artificial Intelligence Research · 2024
Typearticle
Languageen
FieldComputer Science
TopicExplainable Artificial Intelligence (XAI)
Canadian institutionsArtificial Intelligence in Medicine (Canada)University of Alberta
FundersNatural Sciences and Engineering Research Council of CanadaMitacsAustrian Science FundUniversity of AlbertaAlberta Machine Intelligence InstituteCompute CanadaCanadian Institute for Advanced Research
KeywordsHuman-in-the-loopReinforcement learningPosition (finance)Loop (graph theory)Computer scienceReinforcementArtificial intelligenceBusinessPsychologyMathematicsSocial psychology

Abstract

fetched live from OpenAlex

Artificial intelligence (AI) and especially reinforcement learning (RL) have the potential to enable agents to learn and perform tasks autonomously with superhuman performance. However, we consider RL as fundamentally a Human-in-the-Loop (HITL) paradigm, even when an agent eventually performs its task autonomously. In cases where the reward function is challenging or impossible to define, HITL approaches are considered particularly advantageous. The application of Reinforcement Learning from Human Feedback (RLHF) in systems such as ChatGPT demonstrates the effectiveness of optimizing for user experience and integrating their feedback into the training loop. In HITL RL, human input is integrated during the agent’s learning process, allowing iterative updates and fine-tuning based on human feedback, thus enhancing the agent’s performance. Since the human is an essential part of this process, we argue that human-centric approaches are the key to successful RL, a fact that has not been adequately considered in the existing literature. This paper aims to inform readers about current explainability methods in HITL RL. It also shows how the application of explainable AI (xAI) and specific improvements to existing explainability approaches can enable a better human-agent interaction in HITL RL for all types of users, whether for lay people, domain experts, or machine learning specialists. Accounting for the workflow in HITL RL and based on software and machine learning methodologies, this article identifies four phases for human involvement for creating HITL RL systems: (1) Agent Development, (2) Agent Learning, (3) Agent Evaluation, and (4) Agent Deployment. We highlight human involvement, explanation requirements, new challenges, and goals for each phase. We furthermore identify low-risk, high-return opportunities for explainability research in HITL RL and present long-term research goals to advance the field. Finally, we propose a vision of human-robot collaboration that allows both parties to reach their full potential and cooperate effectively.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.004
metaresearch head score (Gemma)0.006
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Review · Consensus signal: Review
Teacher disagreement score0.004
Threshold uncertainty score0.019

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0040.006
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.002
Science and technology studies0.0000.002
Scholarly communication0.0030.004
Open science0.0020.001
Research integrity0.0020.003
Insufficient payload (model declined to judge)0.0030.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.489
GPT teacher head0.457
Teacher spread0.032 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNot applicable
Domainnot available
GenreReview

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations133
Published2024
Admission routes2
Has abstractyes

Explore more

Same venueJournal of Artificial Intelligence ResearchSame topicExplainable Artificial Intelligence (XAI)French-language works237,207