Research map / Reinforcement learning / Visual and representation RL
PROGRESSOR: A Perceptually Guided Reward Estimator with Self-Supervised Online Refinement
Tewodros W. Ayalew, Xiao Zhang, Kevin Yuanbo Wu, Tianchong Jiang, Michael Maire, Matthew R. Walter
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 |
|---|---|---|---|
| add adversarial online push-back refinement of the reward model (ablation) | PROGRESSOR · Meta-World door-open and hammer | episodic return | Improved |
| add push-back refinement (ablation) | PROGRESSOR · Meta-World reach | episodic return | Hurt |
| add online reward updates on non-expert data versus expert-only pretraining (TCN) | PROGRESSOR · Meta-World six tasks | success | Improved |
| weight ACT loss with PROGRESSOR reward instead of uniform weighting | ACT · real-world noisy-demonstration tasks | success rate | Improved |
Closest papers by meaning
- SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning (NeurIPS 2026 · similarity 0.89)
- Subtask-Aware Visual Reward Learning from Segmented Demonstrations (ICLR 2025 · similarity 0.88)
- Progress Reward Model for Reinforcement Learning via Large Language Models (NeurIPS 2025 · similarity 0.88)
- GoalLadder: Incremental Goal Discovery with Vision-Language Models (NeurIPS 2025 · similarity 0.88)
- Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data (ICLR 2024 · similarity 0.88)
- RoboAlign-R1: Distilled Multimodal Reward Alignment for Robot Video World Models (NeurIPS 2026 · 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.
