High entropy leads to symmetry equivariant policies in Dec-POMDPs

Documenti analoghi

• The Yokai Learning Environment: Tracking Beliefs Over Space and Time
  di: Ruhdorfer, Constantin, et al.
  Pubblicazione: (2025)
• The Overcooked Generalisation Challenge: Evaluating Cooperation with Novel Partners in Unknown Environments Using Unsupervised Environment Design
  di: Ruhdorfer, Constantin, et al.
  Pubblicazione: (2024)
• Unsupervised Partner Design Enables Robust Ad-hoc Teamwork
  di: Ruhdorfer, Constantin, et al.
  Pubblicazione: (2025)
• Solving Collaborative Dec-POMDPs with Deep Reinforcement Learning Heuristics
  di: Soffair, Nitsan
  Pubblicazione: (2022)
• Expected Return Symmetries
  di: Muglich, Darius, et al.
  Pubblicazione: (2025)