Research map / Reinforcement learning / Visual and representation RL
ReLAM: Learning Anticipation Model for Rewarding Visual Robotic Manipulation
Nan Tang, Jing-Cheng Pang, Guanlin Li, Chao Qian, Yang Yu
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 |
|---|---|---|---|
| use 4 keypoints instead of 8 or 12 (ablation) | ReLAM · Meta-World Drawer Open | success rate | Improved |
| use piecewise linear reward instead of exponential or logistic (ablation) | ReLAM · Meta-World Drawer Open | success rate | Improved |
| use piecewise linear reward instead of pure linear (ablation) | ReLAM · Meta-World Drawer Open | success rate | Improved |
| generate subgoals with the anticipation model instead of ground-truth keypoint subgoals (ablation) | ReLAM · Meta-World / ManiSkill tasks | success rate | No clear effect |
| represent subgoals as keypoints instead of images (ablation) | ReLAM · Meta-World Drawer Open (online RL) | mean success rate (%): 4.0 -> 100.0 | Improved |
| represent subgoals as keypoints instead of images (ablation) | ReLAM · ManiSkill Push Cube (offline RL) | mean success rate (%): 46.7 -> 89.3 | Improved |
| use ReLAM keypoint distance reward instead of Diffusion Reward | ReLAM · Meta-World Drawer Open (online RL) | mean success rate (%): 80.0 -> 100.0 | Improved |
| use ReLAM keypoint distance reward instead of DACfO | ReLAM · ManiSkill Pick Cube (offline RL) | mean success rate (%): 78.7 -> 88.0 | Improved |
| use ReLAM instead of Diffusion Reward on Door Open | ReLAM · Meta-World Door Open (online RL) | mean success rate (%): 100.0 -> 100.0 | No clear effect |
| use ReLAM instead of ground-truth image subgoal Oracle | ReLAM · Meta-World Button Press Wall (online RL) | mean success rate (%): 76.7 -> 75.8 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Diffusion Reward — Diffusion Reward: Learning Rewards via Conditional Video Diffusion (ECCV 2024) · better on 4 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Multi-Stage Manipulation with Demonstration-Augmented Reward, Policy, and World Model Learning (ICML 2025 · similarity 0.90)
- VICtoR: Learning Hierarchical Vision-Instruction Correlation Rewards for Long-horizon Manipulation (ICLR 2025 · similarity 0.90)
- Subtask-Aware Visual Reward Learning from Segmented Demonstrations (ICLR 2025 · similarity 0.88)
- Scaffolding Dexterous Manipulation with Vision-Language Models (NeurIPS 2025 · similarity 0.87)
- ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics (ICML 2025 · similarity 0.87)
- Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets (ICLR 2025 · similarity 0.87)
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.
