Automated Planning in Repeated Adversarial Games

by   Enrique Munoz de Cote, et al.

Game theory's prescriptive power typically relies on full rationality and/or self-play interactions. In contrast, this work sets aside these fundamental premises and focuses instead on heterogeneous autonomous interactions between two or more agents. Specifically, we introduce a new and concise representation for repeated adversarial (constant-sum) games that highlight the necessary features that enable an automated planing agent to reason about how to score above the game's Nash equilibrium, when facing heterogeneous adversaries. To this end, we present TeamUP, a model-based RL algorithm designed for learning and planning such an abstraction. In essence, it is somewhat similar to R-max with a cleverly engineered reward shaping that treats exploration as an adversarial optimization problem. In practice, it attempts to find an ally with which to tacitly collude (in more than two-player games) and then collaborates on a joint plan of actions that can consistently score a high utility in adversarial repeated games. We use the inaugural Lemonade Stand Game Tournament to demonstrate the effectiveness of our approach, and find that TeamUP is the best performing agent, demoting the Tournament's actual winning strategy into second place. In our experimental analysis, we show hat our strategy successfully and consistently builds collaborations with many different heterogeneous (and sometimes very sophisticated) adversaries.



There are no comments yet.



Reinforcement Learning In Two Player Zero Sum Simultaneous Action Games

Two player zero sum simultaneous action games are common in video games,...

Repeated Quantum Games and Strategic Efficiency

Repeated quantum game theory addresses long term relations among players...

Stochastic Dynamic Games in Belief Space

Information gathering while interacting with other agents is critical in...

Infinitely Split Nash Equilibrium Problems in Repeated Games

In this paper, we introduce the concept of infinitely split Nash equilib...

Filtered Fictitious Play for Perturbed Observation Potential Games and Decentralised POMDPs

Potential games and decentralised partially observable MDPs (Dec-POMDPs)...

Non-Myopic Learning in Repeated Stochastic Games

This paper addresses learning in repeated stochastic games (RSGs) played...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.