Repulsive Population Policy Gradients for Behaviorally Diverse Reinforcement Learning
This work introduces RePPO, which adapts PPO to jointly optimize a compact population of diverse, high-quality policies using a population-dependent, dynamically shaped reward, and shows that directly optimizing compact populations with RePPO provides a scalable approach to QD-RL across increasingly complex domains.
Saeed Hedayatian, Harsh Shah, Celine Mneimneh et al.
· 0 citations