Multiagent Reinforcement Learning: Theoretical Framework and an Algorithm
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
A Cryptographic Solution to a Game Theoretic Problem
CRYPTO '00 Proceedings of the 20th Annual International Cryptology Conference on Advances in Cryptology
Correlated equilibria in graphical games
Proceedings of the 4th ACM conference on Electronic commerce
Computing equilibria in multi-player games
SODA '05 Proceedings of the sixteenth annual ACM-SIAM symposium on Discrete algorithms
Elements of Information Theory (Wiley Series in Telecommunications and Signal Processing)
Elements of Information Theory (Wiley Series in Telecommunications and Signal Processing)
No-regret learning in convex games
Proceedings of the 25th international conference on Machine learning
Modeling how humans reason about others with partial information
Proceedings of the 7th international joint conference on Autonomous agents and multiagent systems - Volume 1
Computing an Extensive-Form Correlated Equilibrium in Polynomial Time
WINE '08 Proceedings of the 4th International Workshop on Internet and Network Economics
A sampling-based approach to computing equilibria in succinct extensive-form games
UAI '09 Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence
Maximum entropy distribution estimation with generalized regularization
COLT'06 Proceedings of the 19th annual conference on Learning Theory
| Hi-index | 0.01 |
Motivated by a machine learning perspective---that game-theoretic equilibria constraints should serve as guidelines for predicting agents' strategies, we introduce maximum causal entropy correlated equilibria (MCECE), a novel solution concept for general-sum Markov games. In line with this perspective, a MCECE strategy profile is a uniquely-defined joint probability distribution over actions for each game state that minimizes the worst-case prediction of agents' actions under log-loss. Equivalently, it maximizes the worst-case growth rate for gambling on the sequences of agents' joint actions under uniform odds. We present a convex optimization technique for obtaining MCECE strategy profiles that resembles value iteration in finite-horizon games. We assess the predictive benefits of our approach by predicting the strategies generated by previously proposed correlated equilibria solution concepts, and compare against those previous approaches on that same prediction task.