Automated Planning in Repeated Adversarial Games

Details Automated Planning in Repeated Adversarial Games Automated Planning in Repeated Adversarial Games

2012-03-15

arxiv.org/abs/1203.3498v1

Computer Science

Computer Science and Game Theory

Appears in Proceedings of the Twenty-Sixth Conference on Uncertainty in Artificial Intelligence (UAI2010)

Scientific paper

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.

Affiliated with

Also associated with

No associations

Rating

Automated Planning in Repeated Adversarial Games does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Automated Planning in Repeated Adversarial Games, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Automated Planning in Repeated Adversarial Games will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-32266