Research map / Reinforcement learning / Visual and representation RL
Learning Generalizable Agents via Saliency-guided Features Decorrelation
Sili Huang, Yanchao Sun, Jifeng Hu, Siyuan Guo, Hechang Chen, Yi Chang, Lichao Sun, Bo Yang
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 |
|---|---|---|---|
| SGFD vs strongest baseline TED/AMBS under background noise (total over 5 tasks) | SGFD · DMC background noise | total reward: 3734.9 -> 3929.5 | Improved |
| SGFD vs AMBS under interpolation of robot parameters | SGFD · DMC interpolation | total reward: 1975.6 -> 2273.4 | Improved |
| SGFD vs AMBS under extrapolation of robot parameters | SGFD · DMC extrapolation | total reward: 1857.6 -> 2253.1 | Improved |
| SGFD vs AMBS on walker-walk with background noise | SGFD · DMC walker-walk background | reward: 926.7 -> 959.1 | Improved |
| SGFD vs DBC on MT-finger-spin interpolation | SGFD · MT-finger-spin | reward: 221.6 -> 234.1 | Improved |
| remove RFF from decorrelation (ablation) | SGFD · Cheetah-run background and MT-cheetah-run | test reward | Hurt |
| decorrelation without RFF vs no decorrelation (ablation) | SGFD ablation · Cheetah-run and MT-cheetah-run | test reward | Improved |
| remove saliency-guided model (global decorrelation of all features) (ablation) | SGFD · Cheetah-run and MT-cheetah-run | test reward | Hurt |
| saliency-guided weighting vs weighting | SGFD · Picking task Pearson correlation of mass feature s10 | correlation | Improved |
| reweight samples with SGFD | SGFD · Visualization of 'fall' states in two environments | share of similar states: 50% and 35.4% -> approximately 42% | Improved |
Closest papers by meaning
- A Simple Framework for Generalization in Visual RL under Dynamic Scene Perturbations (NeurIPS 2024 · similarity 0.90)
- Attention Trajectories as a Diagnostic Axis for Deep Reinforcement Learning (NeurIPS 2026 · similarity 0.88)
- Focus On What Matters: Separated Models For Visual-Based RL Generalization (NeurIPS 2024 · similarity 0.87)
- Zero Shot Generalization of Vision-Based RL Without Data Augmentation (ICML 2025 · similarity 0.87)
- DMR: Decomposed Multi-Modality Representations for Frames and Events Fusion in Visual Reinforcement Learning (CVPR 2024 · similarity 0.87)
- What Effects the Generalization in Visual Reinforcement Learning: Policy Consistency with Truncated Return Prediction (AAAI 2024 · 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.
