Tightening Exploration in Upper Confidence Reinforcement Learning.
Hippolyte BourelOdalric-Ambrym MaillardMohammad Sadegh TalebiPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- reactive planning
- active exploration
- exploration strategy
- action selection
- exploration exploitation
- function approximation
- model based reinforcement learning
- exploration exploitation tradeoff
- learning algorithm
- markov decision processes
- state space
- temporal difference
- autonomous learning
- interactive exploration
- machine learning
- optimal policy
- supervised learning
- model free
- policy search
- active learning
- image processing
- learning problems
- transition model
- dynamic programming
- pattern recognition
- transfer learning