Transformer-Based Deep Reinforcement Learning in VizDoom.
Vitalii SopovIlya MakarovPublished in: AIST (Supplement) (2021)
Keyphrases
- reinforcement learning
- state space
- function approximation
- fuzzy logic
- markov decision processes
- reinforcement learning algorithms
- temporal difference
- optimal policy
- fault diagnosis
- action space
- control problems
- optimal control
- power transformers
- multi agent
- learning algorithm
- transfer learning
- machine learning
- artificial neural networks
- model free
- learning problems
- high voltage
- multi agent reinforcement learning
- robotic control
- autonomous learning
- deep learning
- least squares
- expert systems
- genetic algorithm