floq: Training Critics via Flow-Matching for Scaling Compute in Value-Based RL

Documenti analoghi

• What Does Flow Matching Bring To TD Learning?
  di: Agrawalla, Bhavya, et al.
  Pubblicazione: (2026)
• Compute-Optimal Scaling for Value-Based Deep RL
  di: Fu, Preston, et al.
  Pubblicazione: (2025)
• Value-Based Deep RL Scales Predictably
  di: Rybkin, Oleh, et al.
  Pubblicazione: (2025)
• Is Value Learning Really the Main Bottleneck in Offline RL?
  di: Park, Seohong, et al.
  Pubblicazione: (2024)
• Stop Regressing: Training Value Functions via Classification for Scalable Deep RL
  di: Farebrother, Jesse, et al.
  Pubblicazione: (2024)