Pith. sign in

REVIEW 1 cited by

Hierarchical Reinforcement Learning with Hindsight

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1805.08180 v2 pith:SG2TPGUP submitted 2018-05-21 cs.LG cs.AIcs.NEcs.ROstat.ML

classification cs.LGcs.AIcs.NEcs.ROstat.ML
keywords learningagentshindsightlearnreinforcementsampleabstractionaccelerates
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Reinforcement Learning (RL) algorithms can suffer from poor sample efficiency when rewards are delayed and sparse. We introduce a solution that enables agents to learn temporally extended actions at multiple levels of abstraction in a sample efficient and automated fashion. Our approach combines universal value functions and hindsight learning, allowing agents to learn policies belonging to different time scales in parallel. We show that our method significantly accelerates learning in a variety of discrete and continuous tasks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Mapping State Space using Landmarks for Universal Goal Reaching

    cs.LG 2019-08 conditional novelty 6.0 of 10

    An agent that plans on a landmark graph built from a locally accurate value function reaches long-range goals faster and more reliably than model-free baselines in sparse-reward environments.

Pith tools