pith. sign in

In addition, we also find that settingπref =πϕas done in D2AC policy loss equation 15 rather than just using the actions from the replay bufferπref̸=πϕslightly improves results

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

D2 Actor Critic: Diffusion Actor Meets Distributional Critic

cs.LG · 2025-10-03 · unverdicted · novelty 5.0

D2AC combines a diffusion actor with a distributional critic via fused distributional RL and clipped double Q-learning to reach state-of-the-art results on 18 hard control benchmarks including Humanoid, Dog, and Shadow Hand.

citing papers explorer

Showing 1 of 1 citing paper.

  • D2 Actor Critic: Diffusion Actor Meets Distributional Critic cs.LG · 2025-10-03 · unverdicted · none · ref 40

    D2AC combines a diffusion actor with a distributional critic via fused distributional RL and clipped double Q-learning to reach state-of-the-art results on 18 hard control benchmarks including Humanoid, Dog, and Shadow Hand.