Deep Reinforcement Learning with Swin Transformer.
Li MengMorten GoodwinAnis YazidiPaal EngelstadPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- fuzzy logic
- learning algorithm
- reinforcement learning algorithms
- optimal policy
- decision making
- temporal difference
- markov decision processes
- robotic control
- state space
- dynamic programming
- model free
- fault diagnosis
- learning process
- optimal control
- multi agent
- learning capabilities
- high voltage
- partial discharge
- relational reinforcement learning
- power transformers
- stochastic approximation
- learning problems
- active learning
- case study