Julien Pérolat
YOU?
Author Swipe
View article: Population-based Evaluation in Repeated Rock-Paper-Scissors as a Benchmark for Multiagent Reinforcement Learning
Population-based Evaluation in Repeated Rock-Paper-Scissors as a Benchmark for Multiagent Reinforcement Learning Open
Progress in fields of machine learning and adversarial planning has benefited significantly from benchmark domains, from checkers and the classic UCI data sets to Go and Diplomacy. In sequential decision-making, agent evaluation has largel…
View article: Figure Data for the paper "Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning"
Figure Data for the paper "Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning" Open
Data Release for Article: Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning This package releases a Python notebook reproducing the quantitative figures featured in the research arti…
View article: Figure Data for the paper "Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning"
Figure Data for the paper "Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning" Open
Data Release for Article: Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning This package releases a Python notebook reproducing the quantitative figures featured in the research arti…
View article: Developing, Evaluating and Scaling Learning Agents in Multi-Agent Environments
Developing, Evaluating and Scaling Learning Agents in Multi-Agent Environments Open
The Game Theory & Multi-Agent team at DeepMind studies several aspects of multi-agent learning ranging from computing approximations to fundamental concepts in game theory to simulating social dilemmas in rich spatial environments and trai…
View article: Learning Correlated Equilibria in Mean-Field Games
Learning Correlated Equilibria in Mean-Field Games Open
The designs of many large-scale systems today, from traffic routing environments to smart grids, rely on game-theoretic equilibrium concepts. However, as the size of an $N$-player game typically grows exponentially with $N$, standard game …
View article: Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning
Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning Open
We introduce DeepNash, an autonomous agent capable of learning to play the imperfect information game Stratego from scratch, up to a human expert level. Stratego is one of the few iconic board games that Artificial Intelligence (AI) has no…
View article: Generalization in Mean Field Games by Learning Master Policies
Generalization in Mean Field Games by Learning Master Policies Open
Mean Field Games (MFGs) can potentially scale multi-agent systems to extremely large populations of agents. Yet, most of the literature assumes a single initial distribution for the agents, which limits the practical applications of MFGs. …
View article: Scalable Deep Reinforcement Learning Algorithms for Mean Field Games
Scalable Deep Reinforcement Learning Algorithms for Mean Field Games Open
Mean Field Games (MFGs) have been introduced to efficiently approximate games with very large populations of strategic agents. Recently, the question of learning equilibria in MFGs has gained momentum, particularly using model-free reinfor…
View article: Learning Equilibria in Mean-Field Games: Introducing Mean-Field PSRO
Learning Equilibria in Mean-Field Games: Introducing Mean-Field PSRO Open
Recent advances in multiagent learning have seen the introduction ofa family of algorithms that revolve around the population-based trainingmethod PSRO, showing convergence to Nash, correlated and coarse corre-lated equilibria. Notably, wh…
View article: Scaling up Mean Field Games with Online Mirror Descent
Scaling up Mean Field Games with Online Mirror Descent Open
We address scaling up equilibrium computation in Mean Field Games (MFGs) using Online Mirror Descent (OMD). We show that continuous-time OMD provably converges to a Nash equilibrium under a natural and well-motivated set of monotonicity as…
View article: Concave Utility Reinforcement Learning: the Mean-field Game viewpoint
Concave Utility Reinforcement Learning: the Mean-field Game viewpoint Open
Concave Utility Reinforcement Learning (CURL) extends RL from linear to concave utilities in the occupancy measure induced by the agent's policy. This encompasses not only RL but also imitation learning and exploration, among others. Yet, …
View article: Solving N-player dynamic routing games with congestion: a mean field\n approach
Solving N-player dynamic routing games with congestion: a mean field\n approach Open
The recent emergence of navigational tools has changed traffic patterns and\nhas now enabled new types of congestion-aware routing control like dynamic road\npricing. Using the fundamental diagram of traffic flows - applied in\nmacroscopic…
View article: Solving N-player dynamic routing games with congestion: a mean field approach
Solving N-player dynamic routing games with congestion: a mean field approach Open
The recent emergence of navigational tools has changed traffic patterns and has now enabled new types of congestion-aware routing control like dynamic road pricing. Using the fundamental diagram of traffic flows - applied in macroscopic an…
View article: Shaking the foundations: delusions in sequence models for interaction and control
Shaking the foundations: delusions in sequence models for interaction and control Open
The recent phenomenal success of language models has reinvigorated machine learning research, and large sequence models such as transformers are being applied to a variety of domains. One important problem class that has remained relativel…
View article: Shaking the foundations: delusions in sequence models for interaction\n and control
Shaking the foundations: delusions in sequence models for interaction\n and control Open
The recent phenomenal success of language models has reinvigorated machine\nlearning research, and large sequence models such as transformers are being\napplied to a variety of domains. One important problem class that has remained\nrelati…
View article: Generalization in Mean Field Games by Learning Master Policies
Generalization in Mean Field Games by Learning Master Policies Open
Mean Field Games (MFGs) can potentially scale multi-agent systems to extremely large populations of agents. Yet, most of the literature assumes a single initial distribution for the agents, which limits the practical applications of MFGs. …
View article: Evaluating Strategic Structures in Multi-Agent Inverse Reinforcement Learning
Evaluating Strategic Structures in Multi-Agent Inverse Reinforcement Learning Open
A core question in multi-agent systems is understanding the motivations for an agent's actions based on their behavior. Inverse reinforcement learning provides a framework for extracting utility functions from observed agent behavior, cast…
View article: Mean Field Games Flock! The Reinforcement Learning Way
Mean Field Games Flock! The Reinforcement Learning Way Open
We present a method enabling a large number of agents to learn how to flock. This problem has drawn a lot of interest but requires many structural assumptions and is tractable only in small dimensions. We phrase this problem as a Mean Fiel…
View article: Concave Utility Reinforcement Learning: the Mean-Field Game Viewpoint
Concave Utility Reinforcement Learning: the Mean-Field Game Viewpoint Open
Concave Utility Reinforcement Learning (CURL) extends RL from linear to concave utilities in the occupancy measure induced by the agent's policy. This encompasses not only RL but also imitation learning and exploration, among others. Yet, …
View article: Mean Field Games Flock! The Reinforcement Learning Way
Mean Field Games Flock! The Reinforcement Learning Way Open
We present a method enabling a large number of agents to learn how to flock, which is a natural behavior observed in large populations of animals. This problem has drawn a lot of interest but requires many structural assumptions and is tra…
View article: Mean Field Games Flock! The Reinforcement Learning Way
Mean Field Games Flock! The Reinforcement Learning Way Open
We present a method enabling a large number of agents to learn how to flock,\nwhich is a natural behavior observed in large populations of animals. This\nproblem has drawn a lot of interest but requires many structural assumptions\nand is …
View article: Game Plan: What AI can do for Football, and What Football can do for AI
Game Plan: What AI can do for Football, and What Football can do for AI Open
The rapid progress in artificial intelligence (AI) and machine learning has opened unprecedented analytics possibilities in various team and individual sports, including baseball, basketball, and tennis. More recently, AI techniques have b…
View article: Scaling up Mean Field Games with Online Mirror Descent
Scaling up Mean Field Games with Online Mirror Descent Open
We address scaling up equilibrium computation in Mean Field Games (MFGs) using Online Mirror Descent (OMD). We show that continuous-time OMD provably converges to a Nash equilibrium under a natural and well-motivated set of monotonicity as…
View article: Fictitious Play for Mean Field Games: Continuous Time Analysis and Applications
Fictitious Play for Mean Field Games: Continuous Time Analysis and Applications Open
In this paper, we deepen the analysis of continuous time Fictitious Play learning algorithm to the consideration of various finite state Mean Field Game settings (finite horizon, $γ$-discounted), allowing in particular for the introduction…
View article: Fictitious Play for Mean Field Games: Continuous Time Analysis and\n Applications
Fictitious Play for Mean Field Games: Continuous Time Analysis and\n Applications Open
In this paper, we deepen the analysis of continuous time Fictitious Play\nlearning algorithm to the consideration of various finite state Mean Field Game\nsettings (finite horizon, $\\gamma$-discounted), allowing in particular for the\nint…
View article: Learning to Play No-Press Diplomacy with Best Response Policy Iteration
Learning to Play No-Press Diplomacy with Best Response Policy Iteration Open
Recent advances in deep reinforcement learning (RL) have led to considerable progress in many 2-player zero-sum games, such as Go, Poker and Starcraft. The purely adversarial nature of such games allows for conceptually simple and principl…
View article: Navigating the Landscape of Games.
Navigating the Landscape of Games. Open
Games are traditionally recognized as one of the key testbeds underlying progress in artificial intelligence (AI), aptly referred to as the Drosophila of AI. Traditionally, researchers have focused on using games to build strong AI agents …
View article: Navigating the Landscape of Multiplayer Games to Probe the Drosophila of AI
Navigating the Landscape of Multiplayer Games to Probe the Drosophila of AI Open
Multiplayer games have long been used as testbeds in artificial intelligence research, aptly referred to as the Drosophila of artificial intelligence. Traditionally, researchers have focused on using well-known games to build strong agents…
View article: On the Convergence of Model Free Learning in Mean Field Games
On the Convergence of Model Free Learning in Mean Field Games Open
Learning by experience in Multi-Agent Systems (MAS) is a difficult and exciting task, due to the lack of stationarity of the environment, whose dynamics evolves as the population learns. In order to design scalable algorithms for systems w…
View article: From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization
From Poincaré Recurrence to Convergence in Imperfect Information Games: Finding Equilibrium via Regularization Open
In this paper we investigate the Follow the Regularized Leader dynamics in sequential imperfect information games (IIG). We generalize existing results of Poincaré recurrence from normal-form games to zero-sum two-player imperfect informat…