
The Hanabi Challenge: A New Frontier for AI Research
From the early days of computing, games have been important testbeds for...
read it

From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization
In this paper we investigate the Follow the Regularized Leader dynamics ...
read it

Computing Approximate Equilibria in Sequential Adversarial Games by Exploitability Descent
In this paper, we present exploitability descent, a new algorithm to com...
read it

A Generalized Training Approach for Multiagent Learning
This paper investigates a populationbased training regime based on game...
read it

Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for MultiAgent Intelligence Research
Evolution has produced a multiscale mosaic of interacting adaptive unit...
read it

Variance Reduction in Monte Carlo Counterfactual Regret Minimization (VRMCCFR) for Extensive Form Games using Baselines
Learning strategies for imperfect information games from samples of inte...
read it

Neural Replicator Dynamics
In multiagent learning, agents interact in inherently nonstationary envi...
read it

OpenSpiel: A Framework for Reinforcement Learning in Games
OpenSpiel is a collection of environments and algorithms for research in...
read it

Approximate exploitability: Learning a best response in large games
A common metric in games of imperfect information is exploitability, i.e...
read it

ActorCritic Policy Optimization in Partially Observable Multiagent Environments
Optimization of parameterized policies for reinforcement learning (RL) i...
read it

MemoryEfficient Backpropagation Through Time
We propose a novel approach to reduce memory consumption of the backprop...
read it

ValueDecomposition Networks For Cooperative MultiAgent Learning
We study the problem of cooperative multiagent reinforcement learning w...
read it

Deep Qlearning from Demonstrations
Deep reinforcement learning (RL) has achieved several high profile succe...
read it

Monte Carlo Tree Search with Heuristic Evaluations using Implicit Minimax Backups
Monte Carlo Tree Search (MCTS) has improved the performance of game engi...
read it

Convolution by Evolution: Differentiable Pattern Producing Networks
In this work we introduce a differentiable version of the Compositional ...
read it

NoRegret Learning in ExtensiveForm Games with Imperfect Recall
Counterfactual Regret Minimization (CFR) is an efficient noregret learn...
read it

Multiagent Reinforcement Learning in Sequential Social Dilemmas
Matrix games like Prisoner's Dilemma have guided research on social dile...
read it

Symmetric Decomposition of Asymmetric Games
We introduce new theoretical insights into twopopulation asymmetric gam...
read it

Mastering Chess and Shogi by SelfPlay with a General Reinforcement Learning Algorithm
The game of chess is the most widelystudied domain in the history of ar...
read it

A Unified GameTheoretic Approach to Multiagent Reinforcement Learning
To achieve general intelligence, agents must learn how to interact with ...
read it

A Generalised Method for Empirical Game Theoretic Analysis
This paper provides theoretical bounds for empirical game theoretical an...
read it

Emergent Communication through Negotiation
Multiagent reinforcement learning offers a way to study how communicati...
read it

αRank: MultiAgent Evaluation by Evolution
We introduce αRank, a principled evolutionary dynamics methodology, for...
read it