Deep reinforcement learning with experience replay based on SARSA.
Dongbin ZhaoHaitao WangKun ShaoYuanheng ZhuPublished in: SSCI (2016)
Keyphrases
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- temporal difference learning
- state space
- model free
- learning algorithm
- rl algorithms
- markov decision processes
- transfer learning
- learning problems
- machine learning
- reinforcement learning methods
- optimal policy
- temporal difference
- dynamic programming
- control problems
- function approximators
- eligibility traces
- action selection
- reward function
- multi agent
- mountain car
- supervised learning
- user experience
- fixed point