ScholarGate
アシスタント

手法を比較

選択した手法を並べて確認できます。異なる行はハイライト表示されます。

方策勾配法×深層強化学習×
分野機械学習深層学習
系統Machine learningMachine learning
提唱年19922015
提唱者Ronald Williams (REINFORCE); Sutton et al. (policy gradient theorem)Mnih, V. et al. (DQN)
種類Policy-based reinforcement learningSequential decision-making (agent–environment interaction)
原典Williams, R. J. (1992). Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8(3–4), 229–256. DOI ↗Mnih, V. et al. (2015). Human-Level Control through Deep Reinforcement Learning. Nature, 518, 529–533. DOI ↗
別名REINFORCE, actor-critic, policy optimization, politika gradyanıDerin Pekiştirmeli Öğrenme (DQN / PPO / A3C), derin pekiştirmeli öğrenme, deep RL, DRL
関連44
概要Policy gradient methods are reinforcement-learning algorithms that optimize a parameterized policy directly by gradient ascent on the expected return, rather than learning action-values and acting greedily. Founded on Ronald Williams' 1992 REINFORCE algorithm and the policy gradient theorem of Sutton and colleagues (2000), they naturally handle stochastic and continuous action spaces and underpin modern actor-critic and deep-RL algorithms.Deep Reinforcement Learning combines neural networks with reinforcement learning so an agent learns by interacting with an environment, popularised by Mnih and colleagues' 2015 Nature work on human-level Atari control. Instead of learning from a fixed labelled dataset, the agent takes actions, observes rewards, and gradually shapes a policy that maximises long-run return.
ScholarGateデータセット
  1. v1
  2. 2 出典
  3. PUBLISHED
  1. v1
  2. 2 出典
  3. PUBLISHED

検索へ スライドをダウンロード

ScholarGate手法を比較: Policy Gradient · Deep Reinforcement Learning. 2026-06-17に以下より取得 https://scholargate.app/ja/compare