An Optimization Framework for Task Sequencing in Curriculum Learning

Foglino, Francesco; Christakou, Christiano Coletto; Leonetti, Matteo

doi:10.48550/arxiv.1901.11478

Cited by 1 publication

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For this example we set N m = 400. See [8] for futher details about these examples. Algorithm C 0 requires 1 curriculum evaluation, i.e.…”

Section: Numerical Resultsmentioning

confidence: 99%

“…environments) different from the final task m L , see e.g. [8] and references therein. The curriculum c = (m 0 , .…”

Section: The Curriculum Learning Problemmentioning

confidence: 99%

“…[6,7]. See [8] and the references therein for possible numerical procedures to tackle problem (3). As we show in section 6, the methods proposed in [8] constitute only a preliminary step in order to solve efficiently the curriculum learning problem.…”

Section: The Curriculum Learning Problemmentioning

confidence: 99%

“…c = ∅, but the agent is trained directly to solve the final task m L with starting point θ L = 0 K . -GREEDY Par: Greedy algorithm which constructs the curriculum incrementally by considering at each iteration the n tasks which mostly improve the final performance [8]. This is used as benchmark.…”

Section: Algorithms and Implementation Detailsmentioning

confidence: 99%

“…Curriculum learning is gaining popularity in (deep) reinforcement learning, see e.g. [8] and references therein. It can provide better exploration policies through transfer and generalization from less complex tasks.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Gray-Box Approach for Curriculum Learning

Foglino

Leonetti

Sagratella

et al. 2019

Advances in Intelligent Systems and Computing

Self Cite

View full text Add to dashboard Cite

Curriculum learning is often employed in deep reinforcement learning to let the agent progress more quickly towards better behaviors. Numerical methods for curriculum learning in the literature provides only initial heuristic solutions, with little to no guarantee on their quality. We define a new gray-box function that, including a suitable scheduling problem, can be effectively used to reformulate the curriculum learning problem. We propose different efficient numerical methods to address this gray-box reformulation. Preliminary numerical results on a benchmark task in the curriculum learning literature show the viability of the proposed approach.

show abstract

“…For this example we set N m = 400. See [8] for futher details about these examples. Algorithm C 0 requires 1 curriculum evaluation, i.e.…”

Section: Numerical Resultsmentioning

confidence: 99%

“…environments) different from the final task m L , see e.g. [8] and references therein. The curriculum c = (m 0 , .…”

Section: The Curriculum Learning Problemmentioning

confidence: 99%