pith. sign in

A natural policy gradient

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

Polychromic Objectives for Reinforcement Learning

cs.LG · 2025-09-29 · unverdicted · novelty 5.0

Introduces polychromic objectives adapted into PPO via vine sampling and modified advantages, showing higher success rates and better coverage under perturbations on BabyAI, Minigrid, and algorithmic tasks.

citing papers explorer

Showing 1 of 1 citing paper.

  • Polychromic Objectives for Reinforcement Learning cs.LG · 2025-09-29 · unverdicted · none · ref 14

    Introduces polychromic objectives adapted into PPO via vine sampling and modified advantages, showing higher success rates and better coverage under perturbations on BabyAI, Minigrid, and algorithmic tasks.