Off-Policy Deep Reinforcement Learning with Analogous Disentangled Exploration.
Anji LiuYitao LiangGuy Van den BroeckPublished in: AAMAS (2020)
Keyphrases
- reinforcement learning
- active exploration
- exploration strategy
- action selection
- model based reinforcement learning
- exploration exploitation
- autonomous learning
- exploration exploitation tradeoff
- reinforcement learning algorithms
- function approximation
- machine learning
- state space
- learning algorithm
- markov decision processes
- multi agent
- optimal policy
- model free
- robotic control
- database
- optimal control
- deep learning
- real world
- belief nets
- policy search
- active learning
- unknown environments
- partially observable
- learning capabilities
- temporal difference
- supervised learning
- learning classifier systems
- learning problems