Unverified50% confidenceEventExact time
In 1989, Chris Watkins proposed the Q-learning algorithm, laying the foundation for model-free reinforcement learning.
1
Sources
50%
Confidence
Long-term
Relevance
9/6/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedQ-learning is a value-function method in reinforcement learning, proposed by Watkins in 1989, whose core involves maintaining a Q-table and iteratively updating it via the Bellman equation.78% similarUnverifiedReinforcement learning is one of the three major paradigms of machine learning, and its core idea originates from Skinner's operant conditioning theory in behavioral psychology63% similarUnverifiedGaurav Sen 提出「洋葱模型」学习法，主张将AI学习由外而内逐层剥开，从实际应用开始而非底层数学原理62% similarUnverified布卢姆于20世纪70年代提出掌握学习理论，讨论了结果性评价的局限性62% similarUnverifiedProject-Based Learning (PBL) originates from constructivist learning theory, developed from educator John Dewey's concept of 'learning by doing'.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/863393API
curl https://kongchang.com/api/v1/knowledge/claims/863393MCP
get_claim(id=863393)