Decoupling Exploration and Exploitation in Reinforcement Learning.
Lukas SchäferFilippos ChristianosJosiah HannaStefano V. AlbrechtPublished in: CoRR (2021)
Keyphrases
- exploration exploitation tradeoff
- reinforcement learning
- function approximation
- active exploration
- exploration strategy
- relevance feedback
- action selection
- objective function
- model based reinforcement learning
- input output
- state space
- model free
- active learning
- exploration exploitation
- markov decision processes
- autonomous learning
- learning algorithm
- multi agent
- reinforcement learning algorithms
- decision making
- temporal difference
- case study
- search capabilities
- partially observable
- search strategies
- temporal difference learning
- information visualization
- learning capabilities
- database
- optimal policy
- hidden markov models
- control system
- learning process
- real world