While deep reinforcement learning (RL) has fueled multiple high-profile successes in
machine learning, it is held back from more widespread adoption by its often poor data …

Tremendous progress has been made in reinforcement learning (RL) over the past decade.
Most of these advancements came through the continual development of new algorithms …

Abstract Setting up a well-designed reward function has been challenging for many
reinforcement learning applications. Preference-based reinforcement learning (PbRL) …

Games have a long history as benchmarks for progress in artificial intelligence. Approaches
using search and learning produced strong performance across many perfect information …

Offline reinforcement learning leverages previously collected offline datasets to learn
optimal policies with no necessity to access the real environment. Such a paradigm is also …

Abstract Policy-Space Response Oracles (PSRO) is an influential algorithm framework for
approximating a Nash Equilibrium (NE) in multi-agent non-transitive games. Many previous …

Abstract We introduce the Multi-Agent Tracking Environment (MATE), a novel multi-agent
environment simulates the target coverage control problems in the real world. MATE hosts …

In many practical applications, such as poker, chess, drug interdiction, cybersecurity, and
national defense, players often have adversarial stances, ie, the selfish actions of each …

Recent algorithms have achieved superhuman performance at a number of two-player zero-
sum games such as poker and go. However, many real-world situations are multi-player …

Solution concepts such as Nash Equilibria, Correlated Equilibria, and Coarse Correlated
Equilibria are useful components for many multiagent machine learning algorithms …