Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Learning Others' Intentional Models in Multi-Agent Settings Using Interactive POMDPs
Yanlin Han, Piotr Gmytrasiewicz
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 |
|---|---|---|---|
| increase belief nesting level from 1 to 2 | I-POMDP sampling algorithm · Tiger, N=1000 | running time: 3.68s -> 16m36.07s | Hurt |
| increase belief nesting level from 1 to 2 | I-POMDP sampling algorithm · UAV, N=1000 | running time: 2m1.43s -> 36m19.5s | Hurt |
| increase number of samples from 500 to 2000 | I-POMDP sampling, level 1 · Tiger | running time: 1.96s -> 35.2s | Hurt |
| increase number of samples from 100 to 1000 | I-POMDP sampling, level 1 · UAV | running time: 4.86s -> 2m1.43s | Hurt |
| increase number of particles (ablation) | I-POMDP learning · Tiger and UAV | KL-divergence to ground truth parameters | Improved |
| model the other agent with intentional I-POMDP levels instead of a subintentional frequency-based model | modeling agent i · Tiger and UAV vs level-2 agent j | average reward per time step | Improved |
| use level-3 instead of level-2 modeling (ablation) | modeling agent i · Tiger and UAV | average reward per time step | No clear effect |
Closest papers by meaning
- Learning POMDP World Models from Observations with Language-Model Priors (NeurIPS 2026 · similarity 0.90)
- Factored Online Planning in Many-Agent POMDPs (AAAI 2024 · similarity 0.88)
- Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight (ICLR 2024 · similarity 0.88)
- Multi-Environment POMDPs with Finite-Horizon Objectives (NeurIPS 2026 · similarity 0.88)
- Sequential Monte Carlo for Policy Optimization in Continuous POMDPs (NeurIPS 2025 · similarity 0.87)
- Partially Observable Hierarchical Reinforcement Learning with AI Planning (Student Abstract) (AAAI 2024 · 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.
