---
aliases:
  en:
  - RL
concept_id: reinforcement_learning
preferred:
  en: reinforcement learning
  ja: 強化学習
relations:
  relations:
    broader:
    - machine_learning
    prerequisite:
    - agent
    - reward
    - training
status: active
---

# reinforcement learning

A machine-learning paradigm in which an agent learns a policy for acting in an environment from evaluative feedback, typically by adjusting behavior so as to increase expected cumulative reward or another return-based objective.

## broader

- [machine learning](../terminology/machine_learning.txt)

## prerequisite

- [agent](../terminology/agent.txt)
- [reward](../terminology/reward.txt)
- [training](../terminology/training.txt)

## Documents: mentions

- [既に形成された欺瞞的な方策は、標準的な安全性訓練を経ても残り得る](../documents/hubinger_et_al.deceptive-policies-can-persist-through-safety-training.txt)
- [環境に対称性があると、最適方策は選択肢を保つ方向の power-seeking に傾く](../documents/turner.optimal-policies-tend-to-seek-power.txt)

[Corpus index](../index.txt)