Reinforcement learning — page 2

• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
  arxiv:1801.01290 · 2018-01-04 · text available
• The Multi-Armed Bandit Problem and Its Solutions (Lilian Weng)
  url:lilianweng.github.io/lil-log/2018/01/23/the-multi-armed-bandit-problem-and-its-solutions.html · 2018-01-23 · metadata only
• The Primacy Bias in Deep Reinforcement Learning
  arxiv:2205.07802 · 2022-05-16 · text available
• Towards General-Purpose Model-Free Reinforcement Learning
  arxiv:2501.16142 · 2025-01-27 · text available
• UniMASK: Unified Inference in Sequential Decision Problems
  arxiv:2211.10869 · 2022-11-20 · text available
• Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning
  openreview:XyGJJ4FPoX · 2022-10-01 · text available