On the Sample Efficiency of Abstractions and Potential-Based Reward Shaping in Reinforcement Learning

Documenti analoghi

• Projection Abstractions in Planning Under the Lenses of Abstractions for MDPs
  di: Canonaco, Giuseppe, et al.
  Pubblicazione: (2024)
• Semantic Partial Grounding via LLMs
  di: Canonaco, Giuseppe, et al.
  Pubblicazione: (2026)
• On Learning Action Costs from Input Plans
  di: Morales, Marianela, et al.
  Pubblicazione: (2024)
• Learning Robust Reward Machines from Noisy Labels
  di: Parac, Roko, et al.
  Pubblicazione: (2024)
• Subgoal-based Reward Shaping to Improve Efficiency in Reinforcement Learning
  di: Okudo, Takato, et al.
  Pubblicazione: (2021)