Diversity-Driven Exploration Strategy for Deep Reinforcement Learning.
Zhang-Wei HongTzu-Yun ShannShih-Yang SuYi-Hsiang ChangChun-Yi LeePublished in: CoRR (2018)
Keyphrases
- exploration strategy
- reinforcement learning
- unknown environments
- function approximation
- state space
- markov decision processes
- multiple robots
- multi agent
- single agent
- mobile robot
- optimal policy
- model free
- reinforcement learning algorithms
- locally optimal
- temporal difference
- markov decision problems
- autonomous robots
- machine learning
- global optimization
- linear programming
- dynamic programming