Kaiqing Zhang
Research Assistant
We study provable multi-agent reinforcement learning (MARL) in the gener...
We study a new class of Markov games (MGs), Multi-player Zero-sum
Markov...
Obtaining rigorous statistical guarantees for generalization under
distr...
We study the problem of computing an optimal policy of an infinite-horiz...
Machine learning systems, especially with overparameterized deep neural
...
We study two-player zero-sum stochastic games, and propose a form of
ind...
We propose a new model, independent linear Markov game, for multi-agent
...
We study the task of learning state representations from potentially
hig...
Offline reinforcement learning (RL) concerns pursuing an optimal policy ...
In this paper, we revisit and improve the convergence of policy gradient...
Multi-agent interactions are increasingly important in the context of
re...
Decentralized learning has been advocated and widely deployed to make
ef...
Gradient-based methods have been widely used for system design and
optim...
In this paper, we investigate the power of regularization, a common tech...
Minimax optimization has served as the backbone of many machine learning...
We study sequential decision making problems aimed at maximizing the exp...
We consider a distributed reinforcement learning setting where multiple
...
Certain but important classes of strategic-form games, including zero-su...
We show that computing approximate stationary Markov coarse correlated
e...
We introduce the first direct policy search algorithm which provably
con...
We examine global non-asymptotic convergence properties of policy gradie...
Differentiable simulators promise faster computation time for reinforcem...
Reinforcement learning (RL) has recently achieved tremendous successes i...
Multi-agent reinforcement learning (MARL) algorithms often suffer from a...
We study multi-agent reinforcement learning (MARL) in infinite-horizon
d...
We study the multi-agent safe control problem where agents should avoid
...
Direct policy search serves as one of the workhorses in modern reinforce...
Asynchronous and parallel implementation of standard reinforcement learn...
We consider model-free reinforcement learning (RL) in non-stationary Mar...
In this paper, we study large population multi-agent reinforcement learn...
Model-based reinforcement learning (RL), which finds an optimal policy u...
Monte-Carlo planning, as exemplified by Monte-Carlo Tree Search (MCTS), ...
Multi-agent reinforcement learning (MARL) under partial observability ha...
While the topic of mean-field games (MFGs) has a relatively long history...
This paper proposes a fully asynchronous scheme for policy evaluation
of...
Multi-agent reinforcement learning (MARL) has long been a significant an...
Recent years have witnessed significant advances in reinforcement learni...
Making decisions in the presence of a strategic opponent requires one to...
Policy optimization (PO) is a key ingredient for reinforcement learning ...
In decentralized stochastic control, standard approaches for sequential
...
In this paper, we present a stochastic convergence proof, under suitable...
This paper considers a distributed reinforcement learning problem in whi...
Policy gradient (PG) methods are a widely used reinforcement learning
me...
We study the global convergence of policy optimization for finding the N...
This paper extends off-policy reinforcement learning to the multi-agent ...
This paper studies the distributed reinforcement learning (DRL) problem
...
Despite the increasing interest in multi-agent reinforcement learning (M...
This paper addresses the problem of distributed learning of average beli...
We consider the problem of fully decentralized multi-agent
reinforcement...