Using time-correlated noise to encourage exploration and improve autonomous agents performance in Reinforcement Learning.
Maria J. P. PeixotoAkramul AzimPublished in: FNC/MobiSPC (2021)
Keyphrases
- autonomous agents
- correlated noise
- reinforcement learning
- multi agent
- dynamic environments
- multi agent environments
- multi agent systems
- multiagent systems
- incomplete information
- learning agents
- open systems
- image processing
- function approximation
- coalition formation
- action selection
- agent behavior
- machine learning
- dynamical systems
- win win
- heterogeneous agents
- distributed control
- computational systems
- complex environments
- medical images
- learning algorithm