Research map / Multi-agent systems and games / Games and equilibria
Learning to Incentivize Other Learning Agents
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 |
|---|---|---|---|
| learn incentive function (LIO) instead of independent policy gradient | independent RL agents · Escape Room | collective return | Helped |
| learn incentive function instead of discrete or continuous give-reward actions (PG-d, PG-c) | policy gradient agents · Escape Room | collective return | Helped |
| learn incentive function (LIO) instead of LOLA with reward actions | opponent-shaping agents · Escape Room | collective return | Helped |
| two LIO agents instead of independent learners | IPD agents · Iterated Prisoner's Dilemma | collective return: -2 vs -3 when paired with PG | Helped |
| update incentive after recipients learn rather than 1-episode variant (ablation) | LIO · Asymmetric Escape Room | collective return | Helped |
| fully decentralized opponent modeling (LIO-dec) vs LIO with known opponent parameters (ablation) | LIO · Escape Room | collective return | No clear effect |
| use LIO instead of AC, AC-d, AC-c and inequity aversion | actor-critic agents · Cleanup | collective return | Helped |
Closest papers by meaning
- Reciprocal Reward Influence Encourages Cooperation From Self-Interested Agents (NeurIPS 2024 · similarity 0.89)
- Multi-agent cooperation through learning-aware policy gradients (ICLR 2025 · similarity 0.89)
- Training Generalizable Collaborative Agents via Strategic Risk Aversion (NeurIPS 2026 · similarity 0.88)
- The Distributional Reward Critic Framework for Reinforcement Learning Under Perturbed Rewards (AAAI 2025 · similarity 0.88)
- Learning to Collaborate with Unknown Agents in the Absence of Reward (AAAI 2025 · similarity 0.88)
- O-MAPL: Offline Multi-agent Preference Learning (ICML 2025 · similarity 0.88)
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.