AWESOME: a general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents
From MaRDI portal
Publication:2384141
DOI10.1007/s10994-006-0143-1zbMath1471.91075OpenAlexW2103437045MaRDI QIDQ2384141
Vincent Conitzer, Tuomas W. Sandholm
Publication date: 20 September 2007
Published in: Machine Learning (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/s10994-006-0143-1
Related Items
Belief and truth in hypothesised behaviours, On the Rate of Convergence of Fictitious Play, Autonomous agents modelling other agents: a comprehensive survey and open problems, Making friends on the fly: cooperating with new teammates, On the rate of convergence of fictitious play, Learning to compete, coordinate, and cooperate in repeated games using reinforcement learning, A distributed algorithm to obtain repeated games equilibria with discounting, Negotiating team formation using deep reinforcement learning, AWESOME, Perspectives on multiagent learning, Multi-agent reinforcement learning: a selective overview of theories and algorithms
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Consistency and cautious fictitious play
- Efficient learning equilibrium
- ``Evolutionary selection dynamic in games: Convergence and limit properties
- New complexity results about Nash equilibria
- Simple search methods for finding a Nash equilibrium
- Nash and correlated equilibria: Some complexity considerations
- Subjectivity and correlation in randomized strategies
- The weighted majority algorithm
- Calibrated learning and correlated equilibrium
- A near-optimal polynomial time algorithm for learning in certain classes of stochastic games
- Multiagent learning using a variable learning rate
- Adaptive game playing using multiplicative weights
- Conditional universal consistency.
- Bayesian learning in repeated games of incomplete information
- An iterative method of solving a game
- 10.1162/153244303765208377
- Rational Learning Leads to Nash Equilibrium
- Prediction, Optimization, and Learning in Repeated Games
- A Simple Adaptive Procedure Leading to Correlated Equilibrium
- Learning Theory
- Algorithms, games, and the internet
- Learning Theory and Kernel Machines
- Equilibrium Points of Bimatrix Games
- Equilibrium points in n -person games