shiqi

shiqi

Study GIS, apply to world
twitter
github
bento
jike

reinforcement learning intro-1

介绍#

文档#

表格#

下面的表格基本不能看,因为是 AIGC,网页都是错乱的。

CategoryNameAuthorDescriptionLink
AlgorithmsSARSARichard S. Sutton & Andrew G. BartoA q-learning algorithm that uses Temporal Difference (TD) to update its policy.1
AlgorithmsQ-LearningChristopher J. C. H. Watkins & Peter DayanA model-free reinforcement learning algorithm that learns to predict the expected return for taking a particular action in a particular state.2
AlgorithmsDeep Q-Networks (DQN)Volodymyr Mnih & Geoffrey HintonA neural network-based algorithm that applies Q-learning to play Atari games with high-level controls.3
AlgorithmsDeep Deterministic Policy Gradients (DDPG)John Schulman & Philip MirowskiAn off-policy algorithm for continuous control, using a critic and policy networks.7
AlgorithmsProximal Policy Optimization (PPO)John Schulman & Philip MirowskiA model-free algorithm that uses trust region optimization to update its policy.8
AlgorithmsAdvantage Actor-Critic (A2C)John Schulman & Philip MirowskiAn algorithm that combines the benefits of policy gradient methods and value-based methods.9
FrameworksGymUniversity of Alberta & UberA Python library for reinforcement learning, providing a common interface for implementations of various aspects of the field.4
FrameworksRayRaphaël Sellem & Eric JangA high-level framework for developing and training reinforcement learning models.5
BooksReinforcement LearningRichard S. Sutton & Andrew G. BartoA comprehensive book that covers the basics and applications of reinforcement learning.6
BooksDeep LearningIan Goodfellow, Yoshua Bengio & Aaron CourvilleA comprehensive book on deep learning, including a chapter on reinforcement learning.10
JournalsJournal of Machine Learning ResearchVarious AuthorsA leading journal for machine learning research, including reinforcement learning topics.11
Loading...
Ownership of this post data is guaranteed by blockchain and smart contracts to the creator alone.