Adaptive epsilon-Greedy Exploration in Reinforcement Learning Based on Value Difference.
Michel TokicPublished in: KI (2010)
Keyphrases
- reinforcement learning
- active exploration
- greedy algorithm
- exploration strategy
- dynamic programming
- action selection
- learning capabilities
- optimal control
- model based reinforcement learning
- exploration exploitation
- policy search
- autonomous learning
- adaptive control
- supervised learning
- information retrieval
- function approximation
- theoretical analysis
- greedy heuristic
- state space
- multi agent reinforcement learning
- search algorithm
- machine learning
- neural network
- robotic control
- data sets