A Survey of Linear Value Function Approximation in Reinforcement Learning.
Shicheng GuoXueyu WeiYun XuWei XueXuangou WuBo WeiPublished in: ISICA (2021)
Keyphrases
- reinforcement learning
- linear value function approximation
- reinforcement learning problems
- reinforcement learning algorithms
- function approximation
- markov games
- state space
- markov decision problems
- markov decision processes
- optimal policy
- search space
- model free
- control problems
- multiagent reinforcement learning
- temporal difference
- learning algorithm
- action space
- transfer learning
- multi agent
- action selection
- partially observable
- adaptive control
- markov decision process
- optimal control
- temporal difference learning
- supervised learning
- decision making
- machine learning