Extending GCRL Policy Planning Concepts

igilitschenski · x · 2026-07-09

The author emphasizes again that this work shares the same core idea as other methods: combining planning with learned policies.

Their contribution is implementing this concept on existing pre-trained GCRL policies, using value-based distances, with goals not strictly limited to navigation tasks.

Related event: Research Discusses Improving Pre-trained GCRL Policies(4 posts)→

Original post →

More from Research

Research channel →