pith. sign in

Context-aware policy reuse

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

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

ACCEPT 1

representative citing papers

Combining Trained Models in Reinforcement Learning

cs.LG · 2026-05-04 · accept · novelty 5.0

A review of 15 studies finds positive transfer in DRL mainly when source and target tasks share structure or include alignment mechanisms, but compute-matched comparisons against from-scratch baselines remain rare.

citing papers explorer

Showing 1 of 1 citing paper.

  • Combining Trained Models in Reinforcement Learning cs.LG · 2026-05-04 · accept · none · ref 4

    A review of 15 studies finds positive transfer in DRL mainly when source and target tasks share structure or include alignment mechanisms, but compute-matched comparisons against from-scratch baselines remain rare.