trends.barnas.net

method · first seen 13 Oct 2026

short-horizon actor-critic

Also: SHAC

First-order reinforcement learning that backpropagates through short simulated rollouts to train actor-critic policies.

Mentions per week

0119 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

alternating direction method of multipliersdifferentiable model predictive control