Task diversity produces systematic transfer but inhibits continual reinforcement learning

Documenti analoghi

• Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination
  di: Jha, Kunal, et al.
  Pubblicazione: (2025)
• NiceWebRL: a Python library for human subject experiments with reinforcement learning environments
  di: Carvalho, Wilka, et al.
  Pubblicazione: (2025)
• Modeling Others' Minds as Code
  di: Jha, Kunal, et al.
  Pubblicazione: (2025)
• Predictive representations: building blocks of intelligence
  di: Carvalho, Wilka, et al.
  Pubblicazione: (2024)
• Value Internalization: Learning and Generalizing from Social Reward
  di: Rong, Frieda, et al.
  Pubblicazione: (2024)