arXiv research

This paper tackles learning Stackelberg equilibrium in asymmetric games efficiently from noisy samples.

Policy gradient methods find Nash equilibrium in noisy games.

Algorithm finds ε-equilibrium policies for multi-agent Markov games with hidden low-rank structure.

New RL algorithms find SNE in Markov games with myopic followers.

We consider the problem of finding stationary Nash equilibria (NE) in a finite discounted general-sum stochastic game. We first generalize a non-linear optimization problem from Filar and Vrieze [2004] to a $N$-player setting and break down this problem into simpler sub-problems that ensure there is no Bellman error fo…

Algorithm minimizes regret and converges to equilibria in Markov games.

This paper improves sample efficiency for learning equilibria in multi-player games.

We show by counterexample that policy-gradient algorithms have no guarantees of even local convergence to Nash equilibria in continuous action and state space multi-agent settings. To do so, we analyze gradient-play in N-player general-sum linear quadratic games, a classic game setting which is recently emerging as a b…

New learning dynamics achieve fast convergence in games without needing to know utility scales.

This paper addresses the problem of multi-agent inverse reinforcement learning (MIRL) in a two-player general-sum stochastic game framework. Five variants of MIRL are considered: uCS-MIRL, advE-MIRL, cooE-MIRL, uCE-MIRL, and uNE-MIRL, each distinguished by its solution concept. Problem uCS-MIRL is a cooperative game in…

Efficient reinforcement learning for simultaneous-move zero-sum games using optimistic value iteration.

Model-free learning for multi-agent stochastic games is an active area of research. Existing reinforcement learning algorithms, however, are often restricted to zero-sum games, and are applicable only in small state-action spaces or other simplified settings. Here, we develop a new data efficient Deep-Q-learning method…

We introduce CSE for MLSF games and devise online learning algorithms for achieving no-external Stackelberg-regret.

We formulate a general framework for competitive gradient-based learning that encompasses a wide breadth of multi-agent learning algorithms, and analyze the limiting behavior of competitive gradient-based learning algorithms using dynamical systems theory. For both general-sum and potential games, we characterize a non…

R2-B2 optimizes game interactions with recursive reasoning.

Paper solves learning imperfect-information games with fewer episodes.

Study shows market makers can cooperate without communication.

This work presents a game-theoretic method for AVs that handles imperfect communication and individual rewards.

Algorithm solves online binary classification and infinite games using ERM oracle.

This paper tackles sample-efficient reinforcement learning for partially observable Markov games.

New approach tackles non-stationary multi-agent games with black-box methods.

Paper develops efficient algorithms for learning rationalizable equilibria in multiplayer games.

Novel algorithms for multi-agent reinforcement learning reduce sample complexity.

Paper optimizes multi-agent learning in Markov games with generative model.

Almost all of the work in graphical models for game theory has mirrored previous work in probabilistic graphical models. Our work considers the opposite direction: Taking advantage of recent advances in equilibrium computation for probabilistic inference. We present formulations of inference problems in Markov random f…

Improved model-based reinforcement learning for multi-agent Markov games.

New research shows no-regret learning is impossible in Markov games under certain assumptions.

New algorithms achieve near-optimal cumulative loss in nonparametric online learning and games.

Maker-taker fees can prevent algorithmic cooperation in market making, but not always.

First sample-efficient algorithm for learning EFCE in bandit feedback settings.

Agents learn to give rewards to others in a shared learning environment.

A new algorithm learns policies from batch data in hierarchical RL.

New learning dynamics adapt to corrupted games, improving performance in real-world scenarios.

Can machine learning models for recommendation be easily fooled? While the question has been answered for hand-engineered fake user profiles, it has not been explored for machine learned adversarial attacks. This paper attempts to close this gap. We propose a framework for generating fake user profiles which, when inco…

The paper analyzes RL in high-frequency market making with theoretical and practical implications.

Algorithm improves RL model selection for repeated games with utility maximization.

Unified invariant of knots derived from Verma modules.

GSP improves global average pooling for deep metric learning by learning weights and selecting semantic entities.

In the last few years, deep multi-agent reinforcement learning (RL) has become a highly active area of research. A particularly challenging class of problems in this area is partially observable, cooperative, multi-agent learning, in which teams of agents must learn to coordinate their behaviour while conditioning only…

V-learning tackles multiagent reinforcement learning by reducing sample complexity.

Paper derives estimates for Hessian equations under concavity assumptions.

Paper presents content-based models for game recommendation in cold start scenarios.

In this work, we ask the following question: Can visual analogies, learned in an unsupervised way, be used in order to transfer knowledge between pairs of games and even play one game using an agent trained for another game? We attempt to answer this research question by creating visual analogies between a pair of game…

Potential games, originally introduced in the early 1990's by Lloyd Shapley, the 2012 Nobel Laureate in Economics, and his colleague Dov Monderer, are a very important class of models in game theory. They have special properties such as the existence of Nash equilibria in pure strategies. This note introduces graphical…

IGGP learns game rules from varying quality game play, finding no overall trend.

We introduce a topological combinatorial game called the Region Smoothing Swap Game. The game is played on a game board derived from the connected shadow of a link diagram on a (possibly non-orientable) surface by smoothing at crossings. Moves in the game are performed on regions of the diagram and can switch the direc…

We present a new general board game (GBG) playing and learning framework. GBG defines the common interfaces for board games, game states and their AI agents. It allows one to run competitions of different agents on different games. It standardizes those parts of board game playing and learning that otherwise would be t…

Just as war is sometimes fallaciously represented as a zero sum game -- when in fact war is a negative sum game - stock market trading, a positive sum game over time, is often erroneously represented as a zero sum game. This is called the "zero sum fallacy" -- the erroneous belief that one trader in a stock market exch…