pith. sign in

Title resolution pending

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

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Lever: Inference-Time Policy Reuse under Support Constraints

cs.LG · 2026-04-22 · unverdicted · novelty 6.0

LEVER enables offline composition of pre-trained RL policies via behavioral embeddings and Q-value composition, matching or exceeding training-from-scratch performance in deterministic GridWorld while highlighting limits for long-horizon tasks.

citing papers explorer

Showing 1 of 1 citing paper.

  • Lever: Inference-Time Policy Reuse under Support Constraints cs.LG · 2026-04-22 · unverdicted · none · ref 15

    LEVER enables offline composition of pre-trained RL policies via behavioral embeddings and Q-value composition, matching or exceeding training-from-scratch performance in deterministic GridWorld while highlighting limits for long-horizon tasks.