Towards High-Level Intrinsic Exploration in Reinforcement Learning.
Nicolas BougieRyutaro IchisePublished in: IJCAI (2020)
Keyphrases
- reinforcement learning
- high level
- active exploration
- exploration strategy
- low level
- action selection
- exploration exploitation
- autonomous learning
- model based reinforcement learning
- state space
- higher level
- function approximation
- learning algorithm
- markov decision processes
- exploration exploitation tradeoff
- reinforcement learning algorithms
- machine learning
- object level
- model free
- source code
- temporal difference
- robotic control
- relevance feedback
- dynamic programming
- intermediate level
- neural network
- balancing exploration and exploitation
- multi agent
- active learning
- policy search
- low level features
- markov decision process
- programming language
- geometric structure
- optimal policy