Pith. sign in

REVIEW 1 cited by

JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning

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 2112.04907 v1 pith:QVAOVEJJ submitted 2021-12-07 cs.LG cs.AI

classification cs.LGcs.AI
keywords learningjuewu-mcrepresentationapproachexplorationhierarchicalminecraftperception
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Learning rational behaviors in open-world games like Minecraft remains to be challenging for Reinforcement Learning (RL) research due to the compound challenge of partial observability, high-dimensional visual perception and delayed reward. To address this, we propose JueWu-MC, a sample-efficient hierarchical RL approach equipped with representation learning and imitation learning to deal with perception and exploration. Specifically, our approach includes two levels of hierarchy, where the high-level controller learns a policy to control over options and the low-level workers learn to solve each sub-task. To boost the learning of sub-tasks, we propose a combination of techniques including 1) action-aware representation learning which captures underlying relations between action and representation, 2) discriminator-based self-imitation learning for efficient exploration, and 3) ensemble behavior cloning with consistency filtering for policy robustness. Extensive experiments show that JueWu-MC significantly improves sample efficiency and outperforms a set of baselines by a large margin. Notably, we won the championship of the NeurIPS MineRL 2021 research competition and achieved the highest performance score ever.

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. Select before Act: Spatially Decoupled Action Repetition for Continuous Control

    cs.LG 2025-02 conditional novelty 6.0 of 10

    SDAR performs closed-loop act-or-repeat selection separately for each action dimension, improving sample efficiency and reducing action fluctuation in continuous control.

Pith tools