Stein Variational Goal Generation for adaptive Exploration in Multi-Goal Reinforcement Learning

no code implementations • 14 Jun 2022 • Nicolas Castanet, Sylvain Lamprier, Olivier Sigaud

In multi-goal Reinforcement Learning, an agent can share experience between related training tasks, resulting in better generalization for new tasks at test time.

Multi-Goal Reinforcement Learning reinforcement-learning +1