Enhanced Deep Reinforcement Learning for Parcel Singulation in Non-Stationary Environments.
Jiwei ShenHu LuHao ZhangShujing LyuYue LuPublished in: ICASSP (2024)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- control problems
- state space
- model free
- class imbalance
- multi agent
- non stationary
- artificial intelligence
- optimal policy
- direct policy search
- temporal difference learning
- markov decision processes
- supervised learning
- evolutionary algorithm
- information systems
- search engine