Long N-step Surrogate Stage Reward to Reduce Variances of Deep Reinforcement Learning in Complex Problems.
Junmin ZhongRuofan WuJennie SiPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- solving complex
- complex real world problems
- function approximation
- control problems
- np complete
- post processing
- problems involving
- solving problems
- machine learning
- real world
- learning process
- complex data
- data sets
- learning classifier systems
- learning agent
- reinforcement learning methods
- rl algorithms
- neural network