Do LLM Agents Have Regret? A Case Study in Online Learning and Games.
Chanwoo ParkXiangyu LiuAsuman E. OzdaglarKaiqing ZhangPublished in: CoRR (2024)
Keyphrases
- online learning
- learning agents
- game theoretic
- nash equilibria
- multi agent systems
- multi agent
- minority game
- coalitional games
- e learning
- opponent modeling
- bounded rationality
- multiagent learning
- autonomous agents
- multiple agents
- multiagent systems
- game theory
- stochastic games
- intelligent agents
- solution concepts
- multi agent decision making
- cooperative
- reinforcement learning agents
- coalition formation
- active learning
- computer games
- game players
- video games
- cooperative game
- mixed strategy
- two player games
- online convex optimization
- game design
- software agents
- resource allocation
- case study
- online algorithms
- single agent
- incomplete information
- mobile agents
- dynamic environments
- decision making
- nash equilibrium
- decision problems
- regret bounds
- test bed