Distributional Reinforcement Learning with Sample-set Bellman Update.
Weijian ZhangJianshu WangYang YuPublished in: ICRA (2024)
Keyphrases
- sample set
- reinforcement learning
- training samples
- temporal difference learning
- function approximation
- feature space
- state space
- training data
- hyper sphere
- state action
- model free
- linear program
- piecewise linear
- supervised learning
- reinforcement learning algorithms
- training set
- temporal difference
- robotic control
- neural network
- database
- optimal policy
- co occurrence
- optimal control
- machine learning
- learning process
- actor critic
- learning algorithm
- image processing
- markov decision process
- reinforcement learning methods
- multi agent
- function approximators
- markov decision processes
- feature vectors
- dynamic programming
- transfer learning