General Flexible $f$-divergence for Challenging Offline RL Datasets with Low Stochasticity and Diverse Behavior Policies

Documenti analoghi

• Minding Motivation: The Effect of Intrinsic Motivation on Agent Behaviors
  di: Villalobos-Arias, Leonardo, et al.
  Pubblicazione: (2025)
• Robust Policy Expansion for Offline-to-Online RL under Diverse Data Corruption
  di: He, Longxiang, et al.
  Pubblicazione: (2025)
• Action-Dependent Optimality-Preserving Reward Shaping
  di: Forbes, Grant C., et al.
  Pubblicazione: (2025)
• Potential-Based Intrinsic Motivation: Preserving Optimality With Complex, Non-Markovian Shaping Rewards
  di: Forbes, Grant C., et al.
  Pubblicazione: (2024)
• Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone
  di: Mark, Max Sobol, et al.
  Pubblicazione: (2024)