Grounding Insight: An Artificial Affect Signal for Human-Centric Explainability of RL Agents
cs.HC, cs.AI, cs.LG
Submitted: 2026-09-06
Updated: 2026-09-06
Terminology
Sources
- Improving Human-Robot Teaching by Quantifying and Reducing Mental Model Mismatch
- A Review of Communicating Robot Learning during Human-Robot Interaction
- Credit Assignment: Challenges and Opportunities in Developing Human-like AI Agents
- Can you see how I learn? Human observers' inferences about Reinforcement Learning agents' learning processes
- A Temporal Difference Reinforcement Learning Theory of Emotion: unifying emotion, cognition and adaptive behavior
- In Trust We Survive: Emergent Trust Learning
- Towards Transparency of TD-RL Robotic Systems with a Human Teacher
Related papers
- EmoPhone: A Multi-Wave Dataset for In-the-Wild Mobile and Wearable Affect Sensing
- Tasteply: Externalizing Stable and Situational Preference as Manipulable Spatial Objects
- Shielded Trajectory Sampling for Personalized Relational Safety in Conversational AI
- From Tasks to Turns: Measuring Human Labor Contributions in Human-Agent Joint Production
- Reconstruction and Reflection of Positive Experiences through Resurfacing Laughter-indexed Everyday Moments
- LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems