Log In Sign Up

Competitive Policy Optimization

by   Manish Prajapat, et al.

A core challenge in policy optimization in competitive Markov decision processes is the design of efficient optimization methods with desirable convergence and stability properties. To tackle this, we propose competitive policy optimization (CoPO), a novel policy gradient approach that exploits the game-theoretic nature of competitive games to derive policy updates. Motivated by the competitive gradient optimization method, we derive a bilinear approximation of the game objective. In contrast, off-the-shelf policy gradient methods utilize only linear approximations, and hence do not capture interactions among the players. We instantiate CoPO in two ways:(i) competitive policy gradient, and (ii) trust-region competitive policy optimization. We theoretically study these methods, and empirically investigate their behavior on a set of comprehensive, yet challenging, competitive games. We observe that they provide stable optimization, convergence to sophisticated strategies, and higher scores when played against baseline policy gradient methods.


page 1

page 2

page 3

page 4


Trust Region Policy Optimization of POMDPs

We propose Generalized Trust Region Policy Optimization (GTRPO), a Reinf...

Off-Policy Policy Gradient with State Distribution Correction

We study the problem of off-policy policy optimization in Markov decisio...

Are Deep Policy Gradient Algorithms Truly Policy Gradient Algorithms?

We study how the behavior of deep policy gradient algorithms reflects th...

Independent Policy Gradient Methods for Competitive Reinforcement Learning

We obtain global, non-asymptotic convergence guarantees for independent ...

Stochastic Variance-Reduced Policy Gradient

In this paper, we propose a novel reinforcement- learning algorithm cons...

Emergence of Communication in an Interactive World with Consistent Speakers

Training agents to communicate with one another given task-based supervi...

Neural Replicator Dynamics

In multiagent learning, agents interact in inherently nonstationary envi...

Code Repositories


This repository contains all code and experiments for competitive policy gradient (CoPG) algorithm.

view repo


Extending Competitive Mirror Descent to a multi-agent, reinforcement learning setting.

view repo