pith. sign in

Policy invariance under reward transfor- mations: Theory and application to reward shaping

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

1 Pith paper citing it

fields

cs.MA 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Descent-Guided Policy Gradient for Scalable Cooperative Multi-Agent Learning

cs.MA · 2026-02-23 · unverdicted · novelty 7.0

DG-PG augments policy gradients with descent signals from analytical models to reduce estimator variance from O(N) to O(1), preserve game equilibria, and achieve agent-independent sample complexity while converging on 1500-agent tasks where baselines fail.

citing papers explorer

Showing 1 of 1 citing paper.

  • Descent-Guided Policy Gradient for Scalable Cooperative Multi-Agent Learning cs.MA · 2026-02-23 · unverdicted · none · ref 17

    DG-PG augments policy gradients with descent signals from analytical models to reduce estimator variance from O(N) to O(1), preserve game equilibria, and achieve agent-independent sample complexity while converging on 1500-agent tasks where baselines fail.