Q-learning.

Watkins, C. J. C. H., & Dayan, P. (1992). Q-learning. Machine Learning, 8(3–4), 279-292.

Type

Journal article

Intellectual base

Primary research

Year

1992

DOI

10.1007/bf00992698

Link

https://doi.org/10.1007/BF00992698

Cited from

operations_research

Cited by

3 citations across 3 artifacts.

Primes

• Markov Decision Processes (MDPs)
  • (1963), with substantial development through the 1960s-1980s in applications (inventory management, maintenance, queueing control, game theory).

Domain-specific

• Model-Free Reinforcement Learning
  • Q-learning is one off-policy temporal-difference control algorithm.
• Reinforcement learning
  • Reward defines the agent's formal objective, not moral or social value, and misspecified rewards can produce capable but unwanted behavior.

Verification

This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.

Registry ID ref:df83b24609f0 · see in the full table