MétaCan
Menu
Back to cohort
Record W4287333197 · doi:10.48550/arxiv.2102.02639

Improving Reinforcement Learning with Human Assistance: An Argument for\n Human Subject Studies with HIPPO Gym

2021· preprint· W4287333197 on OpenAlexaff
Matthew E. Taylor, Nicholas N. Nissen, Yuan Wang, Néda Navidi

Bibliographic record

VenuearXiv (Cornell University) · 2021
Typepreprint
Language
FieldComputer Science
TopicReinforcement Learning in Robotics
Canadian institutionsNorthern Alberta Institute of Technology
Fundersnot available
KeywordsReinforcement learningComputer scienceArtificial intelligenceHuman–computer interactionSubject (documents)World Wide Web

Abstract

fetched live from OpenAlex

Reinforcement learning (RL) is a popular machine learning paradigm for game\nplaying, robotics control, and other sequential decision tasks. However, RL\nagents often have long learning times with high data requirements because they\nbegin by acting randomly. In order to better learn in complex tasks, this\narticle argues that an external teacher can often significantly help the RL\nagent learn.\n OpenAI Gym is a common framework for RL research, including a large number of\nstandard environments and agents, making RL research significantly more\naccessible. This article introduces our new open-source RL framework, the Human\nInput Parsing Platform for Openai Gym (HIPPO Gym), and the design decisions\nthat went into its creation. The goal of this platform is to facilitate\nhuman-RL research, again lowering the bar so that more researchers can quickly\ninvestigate different ways that human teachers could assist RL agents,\nincluding learning from demonstrations, learning from feedback, or curriculum\nlearning.\n

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 distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Science and technology studies, Scholarly communication, Research integrity
Consensus categoriesMeta-epidemiology (narrow)
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.665
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.000
Meta-epidemiology (narrow)0.0020.002
Meta-epidemiology (broad)0.0020.000
Bibliometrics0.0010.002
Science and technology studies0.0040.001
Scholarly communication0.0020.002
Open science0.0030.003
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0000.000

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 head0.095
GPT teacher head0.239
Teacher spread0.144 · 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; both teacher heads agree on what is shown here.

Study designSimulation or modeling
Domainnot available
GenreEmpirical

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

Citations0
Published2021
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicReinforcement Learning in RoboticsFrench-language works237,207