One such example is two-player zero-sum Markov games, in which efficient ways to compute a Nash equilibrium are known. Inspired by zero-sum polymatrix normal-form games (Cai et al., 2016), we define a class of zero-sum

Learning from visual observation (LfVO), aiming at recovering policies from only visual observation data, is promising yet a challenging problem.

We present a novel multi-agent RL approach, Selective Multi-Agent Prioritized Experience Relay, in which agents share with other agents a limited number of transitions they observe during training.

Simulation agents are controlled objects that perform realistic behaviors in a virtual world.

We study the problem of generating arbitrarily large environments to improve the throughput of multi-robot systems. Prior work proposes Quality Diversity (QD) algorithms as an effective method for optimizing the environments of automated warehouses. However, these approaches optimize only relatively small environments, falling short when it comes to replicating real-world warehouse sizes. The challenge arises from the exponential increase in the search space as the environment size increases.

Simulation of autonomous vehicle systems requires that simulated traffic participants exhibit diverse and realistic behaviors.

Honguk Woo is the corresponding author.