MétaCan
Menu
Back to cohort

Exploration of the Possibility for a Wider Range of the Discount Factor for Reinforcement Learning

2024· article· en· W4402353118 on OpenAlexaff
Monica Li

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicReinforcement Learning in Robotics
Canadian institutionsPolytechnique Montréal
Fundersnot available
KeywordsReinforcement learningReinforcementRange (aeronautics)Computer scienceFactor (programming language)Artificial intelligenceMachine learningPsychologyEngineeringSocial psychologyAerospace engineeringProgramming language

Abstract

fetched live from OpenAlex

The discount factor for reinforcement learning has been constrained to the range [0, 1] to avoid overestimation of state values during training. Although theoretical studies have indicated that discount factors greater than 1 could be valid for certain tasks, experimental work has generally maintained the [0, 1] limit in flexible discount factor optimization. Our study explores the impact of allowing discount factors to exceed 1 across a variety of reinforcement learning algorithms and classic training environments. Our findings demonstrate that in some grid-based environments, reinforcement learning algorithms with discount factors above 1 can achieve comparable performance to those with discount factors within the [0, 1] range. However, performance tends to be more variable when the discount factor exceeds 1.

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)0.000
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: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.984
Threshold uncertainty score0.203

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0010.000
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 head0.049
GPT teacher head0.298
Teacher spread0.249 · 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.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

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
Published2024
Admission routes1
Has abstractyes

Explore more

Same topicReinforcement Learning in RoboticsFrench-language works237,207