Counting Reward Automata: Sample Efficient Reinforcement Learning Through the Exploitation of Reward Function Structure

Documenti analoghi

• Beyond Sliding Windows: Learning to Manage Memory in Non-Markovian Environments
  di: Tasse, Geraud Nangue, et al.
  Pubblicazione: (2025)
• Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning
  di: Tasse, Geraud Nangue, et al.
  Pubblicazione: (2022)
• Reward Machines for Deep RL in Noisy and Uncertain Environments
  di: Li, Andrew C., et al.
  Pubblicazione: (2024)
• Argumentation and Machine Learning
  di: Rago, Antonio, et al.
  Pubblicazione: (2024)
• Unsupervised Automata Learning via Discrete Optimization
  di: Lutz, Simon, et al.
  Pubblicazione: (2023)