논문 리뷰/Reinforcement Learning

[논문 리뷰] Dueling Network Architectures for Deep Reinforcement Learning (Dueling DQN)

[1511.06581] Dueling Network Architectures for Deep Reinforcement Learning (arxiv.org) Dueling Network Architectures for Deep Reinforcement Learning In recent years there have been many successes of using deep representations in reinforcement learning. Still, many of these applications use conventional architectures, such as convolutional networks, LSTMs, or auto-encoders. In this paper, we pres..

[논문 리뷰] Deep Reinforcement Learning with Double Q-learning (DDQN)

[1509.06461] Deep Reinforcement Learning with Double Q-learning (arxiv.org) Deep Reinforcement Learning with Double Q-learning The popular Q-learning algorithm is known to overestimate action values under certain conditions. It was not previously known whether, in practice, such overestimations are common, whether they harm performance, and whether they can generally be prevented. arxiv.org 이번 논..

[논문 리뷰] Deep Recurrent Q-Learning for Partially Observable MDPs (DRQN)

[1507.06527] Deep Recurrent Q-Learning for Partially Observable MDPs (arxiv.org) Deep Recurrent Q-Learning for Partially Observable MDPs Deep Reinforcement Learning has yielded proficient controllers for complex tasks. However, these controllers have limited memory and rely on being able to perceive the complete game screen at each decision point. To address these shortcomings, this article arxi..

[논문 리뷰] Human-level Control through Deep Reinforcement Learning (DQN)

Human-level control through deep reinforcement learning | Nature 이번에는 Nature지에 발표된 DQN관련된 논문을 리뷰해보고자 한다. Playing Atari with Deep Reinforcement Learning과 거의 같은 저자들이 작성을 했는데 이는 그전 논문에서 여러 가지 실험이 추가된 것이다. 그래서 DQN에 관한 것을 알고 싶다면 밑에 있는 링크를 타고 들어가 읽으면 된다. 이번 리뷰에서는 추가된 실험들만 다루겠다. [논문 리뷰] Playing Atari with Deep Reinforcement Learning (DQN) — LimePencil's Log (tistory.com) [논문 리뷰] Playing Atari with Deep..

[논문 리뷰] Playing Atari with Deep Reinforcement Learning (DQN)

이제부터 이 블로그에 논문을 하나씩 읽으면서 리뷰를 해보려고 한다. 아마 분야마다 시간을 순서대로 큰 영향을 미친 논문을 읽을 것 같다. 이번 논문은 강화학습에 DL을 적용한 첫 번째 성공적인 연구인 Playing Atari with Deep Reinforcement Learning을 읽어보려고 한다. 코드 구현은 다른 글로 해보겠다. [1312.5602] Playing Atari with Deep Reinforcement Learning (arxiv.org) Playing Atari with Deep Reinforcement Learning We present the first deep learning model to successfully learn control policies directly fr..