Reinforcement learning (RL, 강화 학습) is an area of Machine learning inspired by Behaviourist psychology, concerned with how software agents ought to take actions in an environment so as to maximize some notion of cumulative reward. (https://en.wikipedia.org/wiki/Reinforcement_learning)
방법들
- Markov process
- Dynamic programming
- Stochastic process
- Markov decision process
- Finite-Horizon MDP
- Infinite-Horizon MDP
관련자료
관련 포스트
Incoming Links #
Related Articles (Article 0) #
Suggested Pages #
- 0.330 Kubeflow
- 0.062 Deep learning
- 0.057 Naive Bayes classifier
- 0.055 Decision tree
- 0.030 Feature extraction
- 0.025 Hyungyong Kim
- 0.025 September 24
- 0.025 Pattern recognition
- 0.025 Memoization
- 0.024 August 31
- More suggestions...