Research map / Multi-agent systems and games / Games and equilibria
Exploration-Exploitation in Multi-Agent Learning: Catastrophe Theory Meets Game Theory
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 |
|---|---|---|---|
| Increase exploration sufficiently, then reduce it to zero | Smooth Q-learning in aligned-interest coordination games · Pareto Coordination and Stag Hunt | equilibrium selection | Helped |
| Increase exploration sufficiently, then reduce it to zero | Smooth Q-learning in Stag Hunt · Stag Hunt | potential | Hurt |
| Use exploration with a different timing or intensity policy | Smooth Q-learning in Battle of the Sexes · Battle of the Sexes | equilibrium selection | Mixed |
| Increase exploration and then gradually reduce it to zero | Smooth Q-learning in a two-player potential game with 10 actions · Random potential game, 10 actions | potential | Helped |
| Include entropy regularization through the exploration term | Smooth Q-learning · Weighted potential games | convergence to QRE | Helped |
| Use smooth Q-learning with its entropy-regularized cost model | Smooth Q-learning · Arbitrary games | regret | Helped |
| Apply exploration in games with misaligned interests | Smooth Q-learning · Potential games | utility | Mixed |
Closest papers by meaning
- Asymptotic Extinction in Large Coordination Games (AAAI 2025 · similarity 0.92)
- Stability of Multi-Agent Learning in Competitive Networks: Delaying the Onset of Chaos (AAAI 2024 · similarity 0.89)
- Multi-Agent Learning under Uncertainty: Recurrence vs. Concentration (NeurIPS 2025 · similarity 0.89)
- The Horizon Threshold in Cooperative Multi-Agent Reward-Free Exploration (NeurIPS 2026 · similarity 0.89)
- A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning (ICLR 2024 · similarity 0.87)
- Maximizing utility in multi-agent environments by anticipating the behavior of other learners (NeurIPS 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.