MétaCan
Menu
Back to cohort
Record W4287251902 · doi:10.48550/arxiv.2103.15793

LASER: Learning a Latent Action Space for Efficient Reinforcement\n Learning

2021· preprint· W4287251902 on OpenAlexaboutno aff
Arthur Allshire, Roberto Martín-Martín, Charles P. Lin, Shawn Manuel, Silvio Savarese, Animesh Garg

Bibliographic record

VenuearXiv (Cornell University) · 2021
Typepreprint
Language
FieldComputer Science
TopicReinforcement Learning in Robotics
Canadian institutionsnot available
Fundersnot available
KeywordsReinforcement learningAction (physics)Computer scienceArtificial intelligenceSpace (punctuation)Task (project management)Machine learningEngineeringPhysics

Abstract

fetched live from OpenAlex

The process of learning a manipulation task depends strongly on the action\nspace used for exploration: posed in the incorrect action space, solving a task\nwith reinforcement learning can be drastically inefficient. Additionally,\nsimilar tasks or instances of the same task family impose latent manifold\nconstraints on the most effective action space: the task family can be best\nsolved with actions in a manifold of the entire action space of the robot.\nCombining these insights we present LASER, a method to learn latent action\nspaces for efficient reinforcement learning. LASER factorizes the learning\nproblem into two sub-problems, namely action space learning and policy learning\nin the new action space. It leverages data from similar manipulation task\ninstances, either from an offline expert or online during policy learning, and\nlearns from these trajectories a mapping from the original to a latent action\nspace. LASER is trained as a variational encoder-decoder model to map raw\nactions into a disentangled latent action space while maintaining action\nreconstruction and latent space dynamic consistency. We evaluate LASER on two\ncontact-rich robotic tasks in simulation, and analyze the benefit of policy\nlearning in the generated latent action space. We show improved sample\nefficiency compared to the original action space from better alignment of the\naction space to the task space, as we observe with visualizations of the\nlearned action space manifold. Additional details:\nhttps://www.pair.toronto.edu/laser\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)0.002
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Science and technology studies, Scholarly communication, Research integrity
Consensus categoriesMeta-epidemiology (narrow)
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 score0.866
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.001
Meta-epidemiology (narrow)0.0010.002
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.002
Science and technology studies0.0020.000
Scholarly communication0.0010.001
Open science0.0020.005
Research integrity0.0010.004
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 head0.089
GPT teacher head0.214
Teacher spread0.125 · 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; both teacher heads agree on what is shown here.

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
Published2021
Admission routes1
Has abstractyes

Explore more

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