Random curiosity-driven exploration in deep reinforcement learning.
Jing LiXinxin ShiJiehao LiXin ZhangJunzheng WangPublished in: Neurocomputing (2020)
Keyphrases
- reinforcement learning
- active exploration
- exploration strategy
- action selection
- exploration exploitation
- reinforcement learning algorithms
- model based reinforcement learning
- state space
- data driven
- markov decision processes
- function approximation
- machine learning
- optimal policy
- multi agent reinforcement learning
- autonomous learning
- function approximators
- temporal difference
- deep learning
- partially observable
- model free
- dynamic programming
- learning capabilities
- uniformly distributed
- neural network
- website
- information systems
- learning algorithm
- exploration exploitation tradeoff