AWESOME: a general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents
From MaRDI portal
Publication:2384141
Recommendations
Cites work
- 10.1162/153244303765208377
- ``Evolutionary selection dynamic in games: Convergence and limit properties
- A general class of no-regret learning algorithms and game-theoretic equilibria.
- A near-optimal polynomial time algorithm for learning in certain classes of stochastic games
- A Simple Adaptive Procedure Leading to Correlated Equilibrium
- Adaptive game playing using multiplicative weights
- Algorithms, games, and the internet
- An iterative method of solving a game
- Bayesian learning in repeated games of incomplete information
- Calibrated learning and correlated equilibrium
- Conditional universal consistency.
- Consistency and cautious fictitious play
- Efficient learning equilibrium
- Equilibrium points in n -person games
- Equilibrium Points of Bimatrix Games
- scientific article; zbMATH DE number 1233801 (Why is no real title available?)
- scientific article; zbMATH DE number 1306865 (Why is no real title available?)
- scientific article; zbMATH DE number 3205074 (Why is no real title available?)
- Learning Theory
- Multiagent learning using a variable learning rate
- Nash and correlated equilibria: Some complexity considerations
- New complexity results about Nash equilibria
- Prediction, Optimization, and Learning in Repeated Games
- Rational Learning Leads to Nash Equilibrium
- Simple search methods for finding a Nash equilibrium
- Subjectivity and correlation in randomized strategies
- The weighted majority algorithm
Cited in
(24)- Perspectives on multiagent learning
- A hierarchy of prescriptive goals for multiagent learning
- Conjectural equilibrium in multiagent learning
- Colearning in differential games
- Autonomous agents modelling other agents: a comprehensive survey and open problems
- Negotiating team formation using deep reinforcement learning
- Multi-agent reinforcement learning: a selective overview of theories and algorithms
- A distributed algorithm to obtain repeated games equilibria with discounting
- A general criterion and an algorithmic framework for learning in multi-agent systems
- Belief and truth in hypothesised behaviours
- On the rate of convergence of fictitious play
- Making friends on the fly: cooperating with new teammates
- A multiagent reinforcement learning algorithm with non-linear dynamics
- Anytime Self-play Learning to Satisfy Functional Optimality Criteria
- On the rate of convergence of fictitious play
- Learning to compete, coordinate, and cooperate in repeated games using reinforcement learning
- scientific article; zbMATH DE number 2084516 (Why is no real title available?)
- Socially-aware multiagent learning: towards socially optimal outcomes
- On-policy concurrent reinforcement learning
- scientific article; zbMATH DE number 1931819 (Why is no real title available?)
- 10.1162/1532443041827880
- AWESOME
- Evaluation and learning in two-player symmetric games via best and better responses
- The evolutionary dynamics of soft-max policy gradient in multi-agent settings
This page was built for publication: AWESOME: a general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2384141)
