FastDSAC: Unlocking the Potential of Maximum Entropy RL in High-Dimensional Humanoid Control

Documenti analoghi

• Rethinking Soft Actor-Critic in High-Dimensional Action Spaces: The Cost of Ignoring Distribution Shift
  di: Chen, Yanjun, et al.
  Pubblicazione: (2024)
• Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RL
  di: Zhan, Guojian, et al.
  Pubblicazione: (2025)
• DSAC: Distributional Soft Actor-Critic for Risk-Sensitive Reinforcement Learning
  di: Ma, Xiaoteng, et al.
  Pubblicazione: (2020)
• Exact Is Easier: Credit Assignment for Cooperative LLM Agents
  di: Chen, Yanjun, et al.
  Pubblicazione: (2026)
• Revisiting Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning
  di: Zhang, Xiaoyun, et al.
  Pubblicazione: (2025)