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.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Lever: Inference-Time Policy Reuse under Support Constraints
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.