MétaCan
Menu
Back to cohort
Record W2864378606 · doi:10.24963/ijcai.2018/740

Emergent Tangled Program Graphs in Multi-Task Learning

2018· article· en· W2864378606 on OpenAlex
Stephen Kelly, Malcolm I. Heywood

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicEvolutionary Algorithms and Applications
Canadian institutionsDalhousie University
Fundersnot available
KeywordsReinforcement learningComputer scienceTask (project management)Modularity (biology)Representation (politics)Simple (philosophy)Artificial intelligenceProcess (computing)Genetic programmingControl (management)Task analysisHuman–computer interactionMachine learningDistributed computingProgramming language

Abstract

fetched live from OpenAlex

We propose a Genetic Programming (GP) framework to address high-dimensional Multi-Task Reinforcement Learning (MTRL) through emergent modularity. A bottom-up process is assumed in which multiple programs self-organize into collective decision-making entities, or teams, which then further develop into multi-team policy graphs, or Tangled Program Graphs (TPG). The framework learns to play three Atari video games simultaneously, producing a single control policy that matches or exceeds leading results from (game-specific) deep reinforcement learning in each game. More importantly, unlike the representation assumed for deep learning, TPG policies start simple and adaptively complexify through interaction with the task environment, resulting in agents that are exceedingly simple, operating in real-time without specialized hardware support such as GPUs.

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.

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)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.863
Threshold uncertainty score0.231

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
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 head0.025
GPT teacher head0.299
Teacher spread0.274 · 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

Quick stats

Citations3
Published2018
Admission routes1
Has abstractyes

Explore more

Same topicEvolutionary Algorithms and ApplicationsFrench-language works237,207