Engineering Notes
Thoughts and Ideas on AI by Muthukrishnan
Tag: Uncertainty
Distributional Reinforcement Learning and Learning the Full Return Distribution
Move beyond expected returns — learn why modeling the full distribution of rewards unlocks risk-aware agents, better exploration, and state-of-the-art performanceDecision-Making Under Partial Observability with POMDPs
**Partially Observable Markov Decision Processes (POMDPs)** are the mathematical framework for making optimal decisions...