Vision-Based Deep Q-Learning on Simple Control Problems: Stabilization via Neurogenesis Regularization.
Ananto JoyoadikusumoTomas MaulPublished in: BICS (2023)
Keyphrases
- control problems
- reinforcement learning
- optimal control
- continuous state spaces
- reinforcement learning methods
- model free
- queueing systems
- state space
- function approximation
- machine learning
- adaptive control
- reinforcement learning algorithms
- data mining
- real time
- multi agent
- continuous state
- markov decision process
- action selection
- markov decision processes
- optimal policy
- mobile robot