Diversity-Driven Exploration Strategy for Deep Reinforcement Learning.
Zhang-Wei HongTzu-Yun ShannShih-Yang SuYi-Hsiang ChangChun-Yi LeePublished in: ICLR (Workshop) (2018)
Keyphrases
- exploration strategy
- reinforcement learning
- unknown environments
- state space
- locally optimal
- function approximation
- markov decision processes
- model free
- optimal policy
- temporal difference
- learning algorithm
- mobile robot
- machine learning
- single agent
- markov decision problems
- reinforcement learning algorithms
- multi agent
- multiple robots
- optimal control
- action selection
- particle swarm optimisation