When speed matters in learning against adversarial opponents

We propose a novel algorithm that is able to learn and adapt to an opponent even within a limited number of interactions and against a rapidly adapting opponent. The context we use is two player normal form games. We compare the performance of an agent using our algorithm against agents using existing multiagent learning algorithms.

• Publication year

  2012

• Venue

  Adaptive Agents and Multi-Agent Systems

• Publication date

  2012-06-04

• Fields of study

  Computer Science

• Identifiers
  DOI 10.65109/lczq2069
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A general criterion and an algorithmic framework for learning in multi-agent systems

  2007influential reference
• Non-Stationary Policy Learning in 2-Player Zero Sum Games

  2005cited by this paper
• Multiagent learning using a variable learning rate

  2002influential reference
• Leading Best-Response Strategies in Repeated Games

  2001influential reference

• How to Safely Exploit Predictions in General-Sum Normal Form Games

  2015cites this paper
• Fast adaptive learning in repeated stochastic games by game abstraction

  2014cites this paper
• Fast learning against adaptive adversarial opponents

  2012cites this paper