Research map / Reinforcement learning / Visual and representation RL
Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesis
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Add residual forces to RFC-Implicit (ablation) | RFC-Implicit dual-policy control · Human3.6M (Mix) | MAE: 2.610 -> 2.498 | Helped |
| Add residual forces to RFC-Implicit (ablation) | RFC-Implicit dual-policy control · Human3.6M (Mix) | FAE: 3.150 -> 2.893 | Helped |
| Use additive action based on the kinematic policy's predicted joint angles (ablation) | RFC-Implicit dual-policy control · Human3.6M (Mix) | MAE: 3.099 -> 2.498 | Helped |
| Use additive action based on the kinematic policy's predicted joint angles (ablation) | RFC-Implicit dual-policy control · Human3.6M (Mix) | FAE: 3.634 -> 2.893 | Helped |
| Add learnable residual forces to the humanoid control policy | Motion imitation with RFC · Eight agile CMU motion clips | episode return | Helped |
| Use RFC-Explicit instead of RFC-Implicit | Dual-policy control · Human3.6M (Mix), Human3.6M (Cross), and EgoMocap | MAE: 2.498 vs 2.498; 2.379 vs 2.377; 0.557 vs 0.556 | Mixed |
Closest papers by meaning
- Universal Humanoid Motion Representations for Physics-Based Control (ICLR 2024 · similarity 0.89)
- Adversarial Locomotion and Motion Imitation for Humanoid Policy Learning (NeurIPS 2025 · similarity 0.88)
- KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills (NeurIPS 2025 · similarity 0.87)
- Hierarchical World Models as Visual Whole-Body Humanoid Controllers (ICLR 2025 · similarity 0.87)
- SUGAR: A Scalable Human-Video-Driven Generalizable Humanoid Loco-Manipulation Learning Framework (NeurIPS 2026 · similarity 0.87)
- HumanoidArena: Benchmarking Egocentric Hierarchical Whole-body Learning (NeurIPS 2026 · 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.