A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning

by   Dong-Ki Kim, et al.

A fundamental challenge in multiagent reinforcement learning is to learn beneficial behaviors in a shared environment with other simultaneously learning agents. In particular, each agent perceives the environment as effectively non-stationary due to the changing policies of other agents. Moreover, each agent is itself constantly learning, leading to natural non-stationarity in the distribution of experiences encountered. In this paper, we propose a novel meta-multiagent policy gradient theorem that directly accounts for the non-stationary policy dynamics inherent to multiagent learning settings. This is achieved by modeling our gradient updates to consider both an agent's own non-stationary policy dynamics and the non-stationary policy dynamics of other agents in the environment. We show that our theoretically grounded approach provides a general solution to the multiagent learning problem, which inherently comprises all key aspects of previous state of the art approaches on this topic. We test our method on a diverse suite of multiagent benchmarks and demonstrate a more efficient ability to adapt to new agents as they learn than baseline methods across the full spectrum of mixed incentive, competitive, and cooperative domains.


page 1

page 2

page 3

page 4


Agent Probing Interaction Policies

Reinforcement learning in a multi agent system is difficult because thes...

A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning

To achieve general intelligence, agents must learn how to interact with ...

Non-Parametric Stochastic Policy Gradient with Strategic Retreat for Non-Stationary Environment

In modern robotics, effectively computing optimal control policies under...

Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning

In lifelong learning, an agent learns throughout its entire life without...

Deep Reinforcement Learning amidst Lifelong Non-Stationarity

As humans, our goals and our environment are persistently changing throu...

Continual Reinforcement Learning in 3D Non-stationary Environments

High-dimensional always-changing environments constitute a hard challeng...

ROMAX: Certifiably Robust Deep Multiagent Reinforcement Learning via Convex Relaxation

In a multirobot system, a number of cyber-physical attacks (e.g., commun...