Pith. sign in

Updated 2023 Mar

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

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

Compute-Optimal Scaling for Value-Based Deep RL

cs.LG · 2025-08-20 · unverdicted · novelty 5.0

Value-based deep RL shows TD-overfitting: large batches degrade Q-function accuracy for small networks but not large ones, enabling compute-optimal splits between model size and update frequency.

citing papers explorer

Showing 1 of 1 citing paper.

  • Compute-Optimal Scaling for Value-Based Deep RL cs.LG · 2025-08-20 · unverdicted · none · ref 2023

    Value-based deep RL shows TD-overfitting: large batches degrade Q-function accuracy for small networks but not large ones, enabling compute-optimal splits between model size and update frequency.