PersonBellman

Richard Bellman

美国数学家，于1950年代提出马尔可夫决策过程（MDP）和Bellman方程，奠定了动态规划和强化学习的数学基础

Timeline (last 90 days)

Sep 7

The reinforcement learning framework was first proposed by Richard Bellman in the 1950s.

Unverified50%

Sep 6

Richard Bellman proposed dynamic programming theory and the Bellman equation in the 1950s, which remain the mathematical foundation of virtually all RL algorithms to this day.

Unverified50%

All Facts (2)

Unverified

The reinforcement learning framework was first proposed by Richard Bellman in the 1950s.

50%Unverified

Richard Bellman proposed dynamic programming theory and the Bellman equation in the 1950s, which remain the mathematical foundation of virtually all RL algorithms to this day.

50%

Source Articles

Selling Reinforcement Learning Environments: Real Business Opportunity or Phantom Demand?Jul 16