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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| explore with Q-guided flow instead of isotropic Gaussian noise / baseline RL methods | Q-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 efficiency | Improved |
| apply Q-guided flow to Gaussian source samples (ablation) | Gaussian source policy · flow superiority ratio during training | fraction of states with higher Q | Improved |
| vary gradient steps N, step size eta and Euler timestep (ablation) | Q-guided Flow Exploration · MyoLeg-Walk | learning performance | No clear effect |
Closest papers by meaning
- Aligning Flow Map Policies with Optimal $Q$-Guidance (NeurIPS 2026 · similarity 0.87)
- Actor-Free Continuous Control via Structurally Maximizable Q-Functions (NeurIPS 2025 · similarity 0.86)
- Learning from Suboptimal Data in Continuous Control via Auto-Regressive Soft Q-Network (ICML 2025 · similarity 0.86)
- Motion Control of High-Dimensional Musculoskeletal Systems with Hierarchical Model-Based Planning (ICLR 2025 · similarity 0.86)
- Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration (NeurIPS 2026 · similarity 0.86)
- ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning (NeurIPS 2025 · similarity 0.86)
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.
