An overview of multi-agent reinforcement learning from game theoretical perspective
Y Yang, J Wang - arxiv preprint arxiv:2011.00583, 2020 - arxiv.org
Following the remarkable success of the AlphaGO series, 2019 was a booming year that
witnessed significant advances in multi-agent reinforcement learning (MARL) techniques …
witnessed significant advances in multi-agent reinforcement learning (MARL) techniques …
Toward a theoretical foundation of policy optimization for learning control policies
Gradient-based methods have been widely used for system design and optimization in
diverse application domains. Recently, there has been a renewed interest in studying …
diverse application domains. Recently, there has been a renewed interest in studying …
Bellman eluder dimension: New rich classes of rl problems, and sample-efficient algorithms
Finding the minimal structural assumptions that empower sample-efficient learning is one of
the most important research directions in Reinforcement Learning (RL). This paper …
the most important research directions in Reinforcement Learning (RL). This paper …
On the theory of policy gradient methods: Optimality, approximation, and distribution shift
Policy gradient methods are among the most effective methods in challenging reinforcement
learning problems with large state and/or action spaces. However, little is known about even …
learning problems with large state and/or action spaces. However, little is known about even …
Optimality and approximation with policy gradient methods in markov decision processes
Policy gradient (PG) methods are among the most effective methods in challenging
reinforcement learning problems with large state and/or action spaces. However, little is …
reinforcement learning problems with large state and/or action spaces. However, little is …
On the sample complexity of the linear quadratic regulator
This paper addresses the optimal control problem known as the linear quadratic regulator in
the case when the dynamics are unknown. We propose a multistage procedure, called …
the case when the dynamics are unknown. We propose a multistage procedure, called …
Natural policy gradient primal-dual method for constrained markov decision processes
We study sequential decision-making problems in which each agent aims to maximize the
expected total reward while satisfying a constraint on the expected total utility. We employ …
expected total reward while satisfying a constraint on the expected total utility. We employ …
Provably efficient exploration in policy optimization
While policy-based reinforcement learning (RL) achieves tremendous successes in practice,
it is significantly less understood in theory, especially compared with value-based RL. In …
it is significantly less understood in theory, especially compared with value-based RL. In …
Fast global convergence of natural policy gradient methods with entropy regularization
Natural policy gradient (NPG) methods are among the most widely used policy optimization
algorithms in contemporary reinforcement learning. This class of methods is often applied in …
algorithms in contemporary reinforcement learning. This class of methods is often applied in …
Solving a class of non-convex min-max games using iterative first order methods
Recent applications that arise in machine learning have surged significant interest in solving
min-max saddle point games. This problem has been extensively studied in the convex …
min-max saddle point games. This problem has been extensively studied in the convex …