SeRO: Self-Supervised Reinforcement Learning for Recovery from Out-of-Distribution Situations

1 code implementation • 7 Nov 2023 • Chan Kim, Jaekyung Cho, Christophe Bobda, Seung-Woo Seo, Seong-Woo Kim

Moreover, we show that our method can retrain the agent to recover from OOD situations even when in-distribution states are difficult to visit through exploration.