Reinforcement Learning Produces Dominant Strategies for the Iterated Prisoner's Dilemma

by   Marc Harper, et al.

We present tournament results and several powerful strategies for the Iterated Prisoner's Dilemma created using reinforcement learning techniques (evolutionary and particle swarm algorithms). These strategies are trained to perform well against a corpus of over 170 distinct opponents, including many well-known and classic strategies. All the trained strategies win standard tournaments against the total collection of other opponents. The trained strategies and one particular human made designed strategy are the top performers in noisy tournaments also.


page 9

page 14

page 16

page 21


On evolutionary selection of blackjack strategies

We apply the approach of evolutionary programming to the problem of opti...

Optimal foraging strategies can be learned and outperform Lévy walks

Lévy walks and other theoretical models of optimal foraging have been su...

Obtain Employee Turnover Rate and Optimal Reduction Strategy Based On Neural Network and Reinforcement Learning

Nowadays, human resource is an important part of various resources of en...

A meta analysis of tournaments and an evaluation of performance in the Iterated Prisoner's Dilemma

The Iterated Prisoner's Dilemma has been used for decades as a model of ...

A Scalable Reinforcement Learning Approach for Attack Allocation in Swarm to Swarm Engagement Problems

In this work we propose a reinforcement learning (RL) framework that con...

Shaped Policy Search for Evolutionary Strategies using Waypoints

In this paper, we try to improve exploration in Blackbox methods, partic...

Please sign up or login with your details

Forgot password? Click here to reset