BND*-DDQN: Learn to Steer Autonomously Through Deep Reinforcement Learning.
Keyu WuHan WangMahdi Abolfazli EsfahaniShenghai YuanPublished in: IEEE Trans. Cogn. Dev. Syst. (2021)
Keyphrases
- reinforcement learning
- function approximators
- function approximation
- learning agent
- temporal difference
- markov decision processes
- state space
- complex domains
- reinforcement learning algorithms
- action selection
- learning process
- genetic algorithm
- agent receives
- deep learning
- hierarchical reinforcement learning
- fully autonomous
- data mining
- real robot
- optimal control
- unsupervised learning
- search space
- multi agent
- objective function
- learning algorithm