HARL-A: An Extensible Benchmark Framework for Heterogeneous Multi-Agent Adversarial Reinforcement Learning in IsaacLab
HARL-A is presented, an open-source, actively maintained framework built on IsaacLab that enables scalable training and benchmarking of adversarial policies across morphologically diverse robot teams with any number of teams and any mix of robot morphologies per team.
Isaac Peterson, Christopher Allred, Jacob Morrey et al.
· 2 citations
· ⚡1