Unverified50% confidenceFactExact time
时序差分（TD）学习由 Richard Sutton 在1988年正式提出，结合了蒙特卡洛方法和动态规划的优点
1
Sources
50%
Confidence
Long-term
Relevance
8/26/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedRichard Sutton在1990年提出的Dyna架构首次将基于模型的规划与无模型学习统一67% similarUnverifiedRichard Sutton noted in the textbook Reinforcement Learning: An Introduction that Samuel's checkers program is one of the earliest practical implementations of TD learning ideas, predating the formal theorization of TD(λ) by nearly 30 years.62% similarVerifiedSutton and Barto published Reinforcement Learning: An Introduction in 198861% similarUnverifiedRichard Sutton and Andrew Barto systematically formalized the RL theoretical framework in their 1998 book Reinforcement Learning: An Introduction56% similarUnverified智能体-环境交互模型由Richard Sutton和Andrew Barto在1990年代的经典教材中系统化55% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/805329API
curl https://kongchang.com/api/v1/knowledge/claims/805329MCP
get_claim(id=805329)