MétaCan
Menu
Back to cohort
Record W3172765438 · doi:10.48550/arxiv.2012.13658

Locally Persistent Exploration in Continuous Control Tasks with Sparse\n Rewards

2020· preprint· W3172765438 on OpenAlexaff
Susan Amin, Maziar Gomrokchi, Hossein Aboutalebi, Harsh Satija, Doina Precup

Bibliographic record

VenuearXiv (Cornell University) · 2020
Typepreprint
Language
FieldComputer Science
TopicData Visualization and Analytics
Canadian institutionsUniversity of WaterlooMcGill UniversityMila - Quebec Artificial Intelligence Institute
Fundersnot available
KeywordsReinforcement learningComputer scienceState spaceTrajectoryState (computer science)Action (physics)Task (project management)Space (punctuation)Artificial intelligenceAlgorithmMathematicsEngineering

Abstract

fetched live from OpenAlex

A major challenge in reinforcement learning is the design of exploration\nstrategies, especially for environments with sparse reward structures and\ncontinuous state and action spaces. Intuitively, if the reinforcement signal is\nvery scarce, the agent should rely on some form of short-term memory in order\nto cover its environment efficiently. We propose a new exploration method,\nbased on two intuitions: (1) the choice of the next exploratory action should\ndepend not only on the (Markovian) state of the environment, but also on the\nagent's trajectory so far, and (2) the agent should utilize a measure of spread\nin the state space to avoid getting stuck in a small region. Our method\nleverages concepts often used in statistical physics to provide explanations\nfor the behavior of simplified (polymer) chains in order to generate persistent\n(locally self-avoiding) trajectories in state space. We discuss the theoretical\nproperties of locally self-avoiding walks and their ability to provide a kind\nof short-term memory through a decaying temporal correlation within the\ntrajectory. We provide empirical evaluations of our approach in a simulated 2D\nnavigation task, as well as higher-dimensional MuJoCo continuous control\nlocomotion tasks with sparse rewards.\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)0.001
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 score0.981
Threshold uncertainty score0.999

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.002
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0020.001
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 head0.096
GPT teacher head0.207
Teacher spread0.111 · 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

Citations1
Published2020
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicData Visualization and AnalyticsFrench-language works237,207