Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Expected Value of Communication for Planning in Ad Hoc Teamwork
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use EDP-based expected query zones and choose query content by expected value and cost | ad hoc agent in the Tool Fetching domain · Tool Fetching domain, Boltzmann distribution over worker-goal distances | marginal cost | Helped |
| Use EDP-based expected query zones and choose query content by expected value and cost | ad hoc agent in the Tool Fetching domain · Uniform goal distribution | marginal cost | Helped |
| Use EDP-based expected query zones and choose query content by expected value and cost | ad hoc agent in the Tool Fetching domain · Boltzmann distribution favoring closer worker goals | marginal cost | Mixed |
| Use EDP-based expected query zones and choose query content by expected value and cost | ad hoc agent in the Tool Fetching domain · Boltzmann distribution favoring closer worker goals, with increasing per-station query cost | marginal cost | Helped |
| Use EDP-based expected query zones and choose query content by expected value and cost | ad hoc agent in the Tool Fetching domain · Uniform goals, per-station cost ≤ 0.4 | marginal cost | No clear effect |
| Use EDP-based expected query zones and choose query content by expected value and cost | ad hoc agent in the Tool Fetching domain · Boltzmann distribution favoring closer worker goals, per-station cost ≤ 0.2 | marginal cost | No clear effect |
| Increase per-station query cost from 0 to 0.5 | eZ_Q Query · Tool Fetching domain | query count: 23% | Helped |
Closest papers by meaning
- Ad Hoc Teamwork via Offline Goal-Based Decision Transformers (ICML 2025 · similarity 0.88)
- ROTATE: Regret-driven Open-ended Training for Ad Hoc Teamwork (NeurIPS 2026 · similarity 0.87)
- Minimum Coverage Sets for Training Robust Ad Hoc Teamwork Agents (AAAI 2024 · similarity 0.87)
- Open Ad Hoc Teamwork with Cooperative Game Theory (ICML 2024 · similarity 0.86)
- N-agent Ad Hoc Teamwork (NeurIPS 2024 · similarity 0.86)
- Narrowing the Collaboration Gap, Probably (NeurIPS 2026 · 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.