Research map / Reinforcement learning / Visual and representation RL
Diagnosis, Feedback, Adaptation: A Human-in-the-Loop Framework for Test-Time Policy Adaptation
Andi Peng, Aviv Netanyahu, Mark K Ho, Tianmin Shu, Andreea Bobu, Julie Shah, Pulkit Agrawal
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 |
|---|---|---|---|
| show counterfactual demonstrations alongside failed behavior | human diagnosis of shifted concepts in 2D Navigation, Minigrid, and VIMA · 2D Navigation, Minigrid, and VIMA | accuracy of identifying the shifted concept | Improved |
| use counterfactual feedback to identify task-irrelevant concepts for targeted augmentation | policy finetuning on task-irrelevant shifts · 2D Navigation, Minigrid, and VIMA | finetuned policy performance on the user-desired reward | Improved |
| ask users whether proposed counterfactual concepts are irrelevant to their desired reward | DFA users on task-relevant shifts · 2D Navigation, Minigrid, and VIMA | correct rejection of invalid counterfactuals: 79% | Improved |
Closest papers by meaning
- Efficient Test-Time Adaptation For Robot Policies (NeurIPS 2026 · similarity 0.87)
- Reflective Prompted Policy Optimization: Trajectory-Grounded Revision and Salience Bias (NeurIPS 2026 · similarity 0.86)
- VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of Thought (NeurIPS 2024 · similarity 0.86)
- Learning from Trials and Errors: Reflective Test-Time Planning for Embodied LLMs (NeurIPS 2026 · similarity 0.86)
- Behavioral Exploration: Learning to Explore via In-Context Adaptation (ICML 2025 · similarity 0.86)
- GUIDE: Real-Time Human-Shaped Agents (NeurIPS 2024 · similarity 0.85)
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.
