Pith. sign in

For the model update phase, the computational overhead is Oupdate = Oforward + Obackward, (15) where Oforward = Obs1 ∗ B ∗ Nbatches ∗ Nupdate epochs (16) and Obackward = Oforward ∗

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

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

background 1

representative citing papers

Adaptive Data Exploitation in Deep Reinforcement Learning

cs.LG · 2025-01-22 · conditional · novelty 4.0

Adaptively lowering the number of per-episode update epochs via a multi-armed bandit improves or matches PPO/DrAC returns on standard benchmarks while reducing training FLOPS.

citing papers explorer

Showing 1 of 1 citing paper.

  • Adaptive Data Exploitation in Deep Reinforcement Learning cs.LG · 2025-01-22 · conditional · none · ref 1

    Adaptively lowering the number of per-episode update epochs via a multi-armed bandit improves or matches PPO/DrAC returns on standard benchmarks while reducing training FLOPS.