Self-Attention-Based Temporary Curiosity in Reinforcement Learning Exploration.
Hangkai HuShiji SongGao HuangPublished in: IEEE Trans. Syst. Man Cybern. Syst. (2021)
Keyphrases
- reinforcement learning
- active exploration
- action selection
- exploration strategy
- function approximation
- model based reinforcement learning
- exploration exploitation
- state space
- model free
- autonomous learning
- reinforcement learning algorithms
- learning algorithm
- optimal policy
- markov decision processes
- multi agent
- optimal control
- databases
- real world
- machine learning
- temporal difference learning
- robot control
- focus of attention
- temporal difference
- information retrieval
- real time
- visual attention
- artificial neural networks