MétaCan
← all works

A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning

2010· preprint· en· 846 citations· W1931877416 on OpenAlex· 10.1184/r1/6550949

Why is this work in the frame?

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

Canadian funderA Canadian agency funded it. The work may carry no Canadian affiliation at all.

No Canadian affiliation. An affiliation-only frame — the usual design — would never have seen this work. It is one of the works that make the case for inverting the frame.

Abstract

Sequential prediction problems such as imitation learning, where future observations depend on previous predictions (actions), violate the common i.i.d. assumptions made in statistical learning. This leads to poor performance in theory and often in practice. Some recent approaches provide stronger guarantees in this setting, but remain somewhat unsatisfactory as they train either non-stationary or stochastic policies and require a large number of iterations. In this paper, we propose a new iterative algorithm, which trains a stationary deterministic policy, that can be seen as a no regret algorithm in an online learning setting. We show that any such no regret algorithm, combined with additional reduction assumptions, must find a policy with good performance under the distribution of observations it induces in such sequential settings. We demonstrate that this new approach outperforms previous approaches on two challenging imitation learning problems and a benchmark sequence labeling problem.

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.

The record

Venue
arXiv (Cornell University)
Topic
Advanced Bandit Algorithms Research
Field
Decision Sciences
Canadian institutions
Funders
Natural Sciences and Engineering Research Council of CanadaOffice of Naval ResearchMultidisciplinary University Research Initiative
Keywords
RegretComputer scienceBenchmark (surveying)Artificial intelligenceImitationOnline learningReduction (mathematics)Machine learningSequence (biology)Iterative learning controlOnline machine learningConvergence (economics)Mathematical optimizationActive learning (machine learning)MathematicsEconomicsPsychology
Has abstract in OpenAlex
yes