AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Scalable Exploration for High-Dimensional Continuous Control via Value-Guided Flow

Yunyue Wei, Chenhui Zuo, Yanan Sui

ICLR 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Model-based RL with guarantees · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
explore with Q-guided flow instead of isotropic Gaussian noise / baseline RL methodsQ-guided Flow Exploration (actor-critic) · high-dimensional benchmarks (SMPL Humanoid, Unitree H1, MyoHand, MyoLeg, Ostrich)learning efficiency (learning curves)Improved
use Q-guided flow instead of dimension-reduction/muscle-specific baselines (DynSyn, Lattice, DEP-RL)MS-Human-700 walking · MS-Human-700 (700 actuators)learning efficiencyImproved
apply Q-guided flow to Gaussian source samples (ablation)Gaussian source policy · flow superiority ratio during trainingfraction of states with higher QImproved
vary gradient steps N, step size eta and Euler timestep (ablation)Q-guided Flow Exploration · MyoLeg-Walklearning performanceNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy