MétaCan
Menu
Back to cohort
Record W4302917494 · doi:10.48550/arxiv.1806.06161

BaRC: Backward Reachability Curriculum for Robotic Reinforcement\n Learning

2018· preprint· en· W4302917494 on OpenAlexfundno aff
Boris Ivanovic, J. Harrison, Apoorva Sharma, Mo Chen, Marco Pavone

Bibliographic record

VenuearXiv (Cornell University) · 2018
Typepreprint
Languageen
FieldComputer Science
TopicReinforcement Learning in Robotics
Canadian institutionsnot available
FundersOffice of Naval ResearchNatural Sciences and Engineering Research Council of CanadaToyota Research Institute
KeywordsReinforcement learningComputer scienceLeverage (statistics)BottleneckReachabilityPrior probabilityFlexibility (engineering)Artificial intelligenceOptimal controlCurriculumMathematical optimizationMachine learningBayesian probabilityTheoretical computer scienceMathematics

Abstract

fetched live from OpenAlex

Model-free Reinforcement Learning (RL) offers an attractive approach to learn\ncontrol policies for high-dimensional systems, but its relatively poor sample\ncomplexity often forces training in simulated environments. Even in simulation,\ngoal-directed tasks whose natural reward function is sparse remain intractable\nfor state-of-the-art model-free algorithms for continuous control. The\nbottleneck in these tasks is the prohibitive amount of exploration required to\nobtain a learning signal from the initial state of the system. In this work, we\nleverage physical priors in the form of an approximate system dynamics model to\ndesign a curriculum scheme for a model-free policy optimization algorithm. Our\nBackward Reachability Curriculum (BaRC) begins policy training from states that\nrequire a small number of actions to accomplish the task, and expands the\ninitial state distribution backwards in a dynamically-consistent manner once\nthe policy optimization algorithm demonstrates sufficient performance. BaRC is\ngeneral, in that it can accelerate training of any model-free RL algorithm on a\nbroad class of goal-directed continuous control MDPs. Its curriculum strategy\nis physically intuitive, easy-to-tune, and allows incorporating physical priors\nto accelerate training without hindering the performance, flexibility, and\napplicability of the model-free RL algorithm. We evaluate our approach on two\nrepresentative dynamic robotic learning problems and find substantial\nperformance improvement relative to previous curriculum generation techniques\nand naive exploration strategies.\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: Methods · Consensus signal: none
Teacher disagreement score0.965
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0000.001
Open science0.0030.004
Research integrity0.0010.001
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 head0.063
GPT teacher head0.211
Teacher spread0.147 · 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
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
Published2018
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicReinforcement Learning in RoboticsFrench-language works237,207