Tags | Planning | Learning | Decentralized | Agent | Dev

Reinforcement Learning | Alphabetic | Primary | Latest | Earliest

• From Policy Gradient to PPO
  PPO, one of the most widely-used RL algorithms.
• Understanding Bellman Equations
  Why and how are Bellman equations used in RL?

Multi-Agent Systems | Alphabetic | Primary | Latest | Earliest

• A Brief Introduction to Dec-POMDP
  About Dec-POMDP, its computation, and planning.
• Optimal Q-functions for Dec-POMDP
  Why can't we compute π^* via normative definition of Q^* in Dec-POMDP?

Generative AI | Alphabetic | Primary | Latest | Earliest

• A Brief Introduction to Diffusion Models
  Math foundations of diffusion models.
• Reward Modeling in LLM Alignment
  How the reward models in RLHF are built?

See instructions here. If you spot anything off, please send me an email.