PDiT: Interleaving Perception and Decision-making Transformers for Deep Reinforcement Learning.
Hangyu MaoRui ZhaoZiyue LiZhiwei XuHao ChenYiqun ChenBin ZhangZhen XiaoJunge ZhangJiangjin YinPublished in: AAMAS (2024)
Keyphrases
- reinforcement learning
- decision making
- action selection
- decision makers
- active exploration
- function approximation
- fuzzy logic
- temporal difference
- decision support
- information processing
- machine learning
- learning algorithm
- supervised learning
- optimal policy
- supply chain
- state space
- dynamic programming
- reinforcement learning algorithms
- multi criteria
- neural network
- stochastic approximation
- group decision making
- data mining
- visual perception
- optimal control
- learning problems
- markov decision processes
- dynamical systems
- multi agent
- real time
- decision support system
- knowledge management