Multiagent learning using a variable learning rate
Artificial Intelligence
Predicting the Expected Behavior of Agents that Learn About Agents: The CLRI Framework
Autonomous Agents and Multi-Agent Systems
Friend-or-Foe Q-learning in General-Sum Games
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Learning to Reach the Pareto Optimal Nash Equilibrium as a Team
AI '02 Proceedings of the 15th Australian Joint Conference on Artificial Intelligence: Advances in Artificial Intelligence
Nash Convergence of Gradient Dynamics in General-Sum Games
UAI '00 Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence
Implicit Negotiation in Repeated Games
ATAL '01 Revised Papers from the 8th International Workshop on Intelligent Agents VIII
Towards a pareto-optimal solution in general-sum games
AAMAS '03 Proceedings of the second international joint conference on Autonomous agents and multiagent systems
Nash q-learning for general-sum stochastic games
The Journal of Machine Learning Research
A polynomial-time Nash equilibrium algorithm for repeated games
Decision Support Systems - Special issue: The fourth ACM conference on electronic commerce
Cooperative Multi-Agent Learning: The State of the Art
Autonomous Agents and Multi-Agent Systems
Learning to compete, compromise, and cooperate in repeated general-sum games
ICML '05 Proceedings of the 22nd international conference on Machine learning
Evolutionary game theory and multi-agent reinforcement learning
The Knowledge Engineering Review
Existence of multiagent equilibria with limited agents
Journal of Artificial Intelligence Research
Satisficing and learning cooperation in the prisoner's dilemma
IJCAI'01 Proceedings of the 17th international joint conference on Artificial intelligence - Volume 1
On the analysis of reputation for agent-based web services
Expert Systems with Applications: An International Journal
Comparative evaluation of MAL algorithms in a diverse set of ad hoc team problems
Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems - Volume 1
Learning to achieve socially optimal solutions in general-sum games
PRICAI'12 Proceedings of the 12th Pacific Rim international conference on Trends in Artificial Intelligence
Strategic adaptation of humans playing computer algorithms in a repeated constant-sum game
Autonomous Agents and Multi-Agent Systems
Hi-index | 0.00 |
We consider the learning problem faced by two self-interested agents repeatedly playing a general-sum stage game. We assume that the players can observe each other's actions but not the payoffs received by the other player. The concept of Nash Equilibrium in repeated games provides an individually rational solution for playing such games and can be achieved by playing the Nash Equilibrium strategy for the single-shot game in every iteration. Such a strategy, however can sometimes lead to a Pareto-Dominated outcome for games like Prisoner's Dilemma. So we prefer learning strategies that converge to a Pareto-Optimal outcome that also produces a Nash Equilibrium payoff for repeated two-player, n-action general-sum games. The Folk Theorem enable us to identify such outcomes. In this paper, we introduce the Conditional Joint Action Learner (CJAL) which learns the conditional probability of an action taken by the opponent given its own actions and uses it to decide its next course of action. We empirically show that under self-play and if the payoff structure of the Prisoner's Dilemma game satisfies certain conditions, a CJAL learner, using a random exploration strategy followed by a completely greedy exploitation technique, will learn to converge to a Pareto-Optimal solution. We also show that such learning will generate Pareto-Optimal payoffs in a large majority of other two-player general sum games. We compare the performance of CJAL with that of existing algorithms such as WOLF-PHC and JAL on all structurally distinct two-player conflict games with ordinal payoffs.