Research map / Reinforcement learning / Visual and representation RL
A Low-Cost Ethics Shaping Approach for Designing Reinforcement Learning Agents
Yueh-Hua Wu, Shou-De Lin
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 ethics shaping based on human behavior data | SARSA · Grab a Milk | non-crying babies crossed | Improved |
| Add ethics shaping based on human behavior data | SARSA · Grab a Milk | crying babies helped | Improved |
| Add ethics shaping based on human behavior data | SARSA · Grab a Milk | convergence | No clear effect |
| Add ethics shaping based on human behavior data | SARSA · Driving and Avoiding | cumulative reward | No clear effect |
| Add ethics shaping based on human behavior data | SARSA · Driving and Avoiding | collisions | No clear effect |
| Add ethics shaping based on human behavior data | SARSA · Driving and Avoiding | cats hit | Improved |
| Add ethics shaping based on human behavior data | SARSA · Driving and Rescuing | elders rescued | Improved |
| Add ethics shaping based on human behavior data | SARSA · Driving and Rescuing | collisions | No clear effect |
| Add ethics shaping based on human behavior data | SARSA · Driving and Rescuing | cumulative reward | Hurt |
Closest papers by meaning
- Moral Alignment for LLM Agents (ICLR 2025 · similarity 0.86)
- MoralReason: Generalizable Moral Decision Alignment for LLM Agents Using Reasoning-Level Reinforcement Learning (AAAI 2026 · similarity 0.85)
- ME: Modelling Ethical Values for Value Alignment (AAAI 2025 · similarity 0.85)
- Human-Guided Moral Decision Making in Text-Based Games (AAAI 2024 · similarity 0.84)
- Operationalising Rawlsian Ethics for Fairness in Norm Learning Agents (AAAI 2025 · similarity 0.83)
- An Evolutionary Perspective on AI Alignment (Student Abstract) (AAAI 2025 · similarity 0.82)
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.
