Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Learning Models of Sequential Decision-Making with Partial Specification of Agent Behavior
Vaibhav V. Unhelkar, Julie A. Shah
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 local change-point input (ablation) | VI · Line World | wKL(Tx): 2.01 -> 1.38 | Improved |
| add global Tx constraints via CVI (ablation) | VI · Line World | wKL(Tx): 2.01 -> 0.98 | Improved |
| add both auxiliary inputs (ablation) | VI · Line World | Hamming dist. (test): 0.53 -> 0.14 | Improved |
| add both auxiliary inputs (ablation) | VI · Highway | wKL(Tx): 2.11 -> 0.64 | Improved |
| add both auxiliary inputs (ablation) | VI · Highway | wKL(bx): 1.67 -> 1.58 | No clear effect |
| add local change-point input (ablation) | VI · Highway | Hamming dist. (train): 0.56 -> 0.36 | Improved |
| add global Tx constraints via CVI (ablation) | VI · Highway | Hamming dist. (train): 0.56 -> 0.48 | Improved |
| add local input (ablation) | VI · Line World | wKL(bx): 0.85 -> 0.87 | No clear effect |
| add global input (ablation) | VI-L · Highway | wKL(bx): 1.75 -> 1.50 | Mixed |
| model unknown states with AMM (VI) instead of MaxEnt IRL | policy alignment · Line World | wKL(pi): 1.08 -> 0.77 | Improved |
Closest papers by meaning
- Mental-Models for Multi-Agent Systems (NeurIPS 2026 · similarity 0.88)
- AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model (ICLR 2024 · similarity 0.87)
- Understanding the Learning Dynamics of Alignment with Human Feedback (ICML 2024 · similarity 0.87)
- Learning POMDP World Models from Observations with Language-Model Priors (NeurIPS 2026 · similarity 0.86)
- The Limits of Predicting Agents from Behaviour (ICML 2025 · similarity 0.86)
- General agents need world models (ICML 2025 · similarity 0.86)
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.
