Bregman Centroid Guided Cross-Entropy Method

Documenti analoghi

• Observations Meet Actions: Learning Control-Sufficient Representations for Robust Policy Generalization
  di: Gu, Yuliang, et al.
  Pubblicazione: (2025)
• Proto-MPC: An Encoder-Prototype-Decoder Approach for Quadrotor Control in Challenging Winds
  di: Gu, Yuliang, et al.
  Pubblicazione: (2024)
• Action Mapping for Reinforcement Learning in Continuous Environments with Constraints
  di: Theile, Mirco, et al.
  Pubblicazione: (2024)
• Physics-Regulated Deep Reinforcement Learning: Invariant Embeddings
  di: Cao, Hongpeng, et al.
  Pubblicazione: (2023)
• Physics-model-guided Worst-case Sampling for Safe Reinforcement Learning
  di: Cao, Hongpeng, et al.
  Pubblicazione: (2024)