Pith. sign in

Solving the rubik’s cube with deep reinforcement learning and search

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 1

years

2024 1

verdicts

REJECT 1

roles

background 1

polarities

support 1

representative citing papers

Solving Rubik's Cube Without Tricky Sampling

cs.LG · 2024-11-29 · reject · novelty 5.0

The paper presents a PPO policy trained with rewards from a learned cost model, claiming 99.4% success on the 2x2x2 Rubik's Cube without search or solved-state sampling, but with weak evidential support.

citing papers explorer

Showing 1 of 1 citing paper.

  • Solving Rubik's Cube Without Tricky Sampling cs.LG · 2024-11-29 · reject · none · ref 2

    The paper presents a PPO policy trained with rewards from a learned cost model, claiming 99.4% success on the 2x2x2 Rubik's Cube without search or solved-state sampling, but with weak evidential support.