MétaCan
Menu
Back to cohort
Record W1514336978

Effective Learning in Adaptive Dynamic Systems.

2007· article· en· W1514336978 on OpenAlexaff
Andriy Burkov, Brahim Chaib-draa

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldDecision Sciences
TopicGame Theory and Applications
Canadian institutionsUniversité Laval
Fundersnot available
KeywordsComputer scienceClass (philosophy)Set (abstract data type)Mathematical optimizationReinforcement learningInterdependenceExploitPareto principleArtificial intelligenceMathematics
DOInot available

Abstract

fetched live from OpenAlex

Classically, an approach to the policy learning in multia-gent systems supposed that the agents, via interactions and/or by using preliminary knowledge about the reward functions of all players, would find an interdependent solution called “equilibrium”. Recently, however, certain researchers ques-tion the necessity and the validity of the concept of equilib-rium as the most important multiagent solution concept. They argue that a “good ” learning algorithm is one that is efficient with respect to a certain class of counterparts. Adaptive play-ers is an important class of agents that learn their policies sep-arately from the maintenance of the beliefs about their coun-terparts ’ future actions and make their decisions based on that policy and the current belief. In this paper we propose an ef-ficient learning algorithm in presence of the adaptive coun-terparts called Adaptive Dynamics Learner (ADL) which is able to learn an efficient policy over the opponents ’ adaptive dynamics rather than over the simple actions and beliefs and, by so doing, to exploit this dynamics to obtain a higher util-ity than any equilibrium strategy can provide. We tested our algorithm on a big set of the most known and demonstrative matrix games and observed that ADL agent is highly efficient against Adaptive Play Q-learning (APQ) agent and Infinites-imal Gradient Ascent (IGA) agent. In self-play, when possi-ble, ADL is able to converge to a Pareto optimal strategy that maximizes the welfare of all players instead of an equilibrium strategy.

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)0.005
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesInsufficient payload (model declined to judge)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.618
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0050.001
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)0.0000.001

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 head0.045
GPT teacher head0.393
Teacher spread0.347 · 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 teacher head, not a consensus.

Study designTheoretical or conceptual
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

Citations3
Published2007
Admission routes1
Has abstractyes

Explore more

Same topicGame Theory and ApplicationsFrench-language works237,207