method · first seen 15 Oct 2026
reinforcement learning from pretrained policies
Reusing pretrained reinforcement learning policies as priors to guide new policy learning or planning.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Manifold Generative Annealing for Contact Constraint-aware Impedance Control with Reinforcement Learning PriorPapers · 15 Oct 2026 · Zhilin He, Guoquan Qi, Changliu Liu
Latest sources
- Manifold Generative Annealing for Contact Constraint-aware Impedance Control with Reinforcement Learning PriorPapers · 15 Oct 2026 · Zhilin He, Guoquan Qi, Changliu Liu