Exploration in deep reinforcement learning: A survey.
Pawel LadoszLilian WengMinwoo KimHyondong OhPublished in: Inf. Fusion (2022)
Keyphrases
- reinforcement learning
- active exploration
- exploration strategy
- action selection
- exploration exploitation
- model based reinforcement learning
- function approximation
- autonomous learning
- temporal difference
- model free
- exploration exploitation tradeoff
- reinforcement learning algorithms
- learning algorithm
- active learning
- markov decision processes
- state space
- supervised learning
- hidden markov models
- balancing exploration and exploitation
- partially observable
- real robot
- multi agent
- data sets
- real world
- robotic control
- information retrieval
- artificial neural networks
- temporal difference learning
- learning process
- database