MétaCan
Menu
Back to cohort
Record W4311681064 · doi:10.22215/etd/2022-15178

Learning Transition Dynamics via Rewarded Exploration: A Study using Unity's MLAgents

2022· dissertation· en· W4311681064 on OpenAlexaff
Jacob Tynski

Bibliographic record

Venuenot available
Typedissertation
Languageen
FieldComputer Science
TopicReinforcement Learning in Robotics
Canadian institutionsCarleton University
Fundersnot available
KeywordsComputer sciencePopularityArtificial intelligenceHyperparameterTransition (genetics)Action (physics)Dynamics (music)Variable (mathematics)Focus (optics)Artificial neural networkState (computer science)Game engineMachine learningWork (physics)Human–computer interactionEngineeringPsychologySocial psychology

Abstract

fetched live from OpenAlex

AI agents can benefit from understanding their environment and how it works, as being able to predict the state of the environment after one makes an action is useful for doing tasks. My work explores using a custom reward system to guide an AI agent in learning the transition dynamics of its environment via exploration. Due to the popularity of game engines, I focus on building a transition dynamics model using the game engine, Unity, which provides a package for making AI agents. I test the agent's behaviour across 8 studies, with different hyperparameters for its neural network and with and without access to memory via Long Short-Term Memory. I also conducted two tests with a different reward system to help judge the effectiveness of my approach.

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)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
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 score0.931
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0000.001
Open science0.0010.000
Research integrity0.0000.001
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 head0.033
GPT teacher head0.300
Teacher spread0.267 · 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 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
Published2022
Admission routes1
Has abstractyes

Explore more

Same topicReinforcement Learning in RoboticsFrench-language works237,207