Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?
Yang DaiOubo MaLongfei ZhangXingxing LiangShengchao HuMengzhu WangShouling JiJincai HuangLi ShenPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- optimization problems
- optimization method
- discrete optimization
- data sets
- trajectory data
- optimization model
- optimization algorithm
- global optimization
- real time
- reinforcement learning algorithms
- optimization process
- optimization methods
- state space
- constrained optimization
- dynamic programming
- learning process
- multi agent
- database
- optimization strategies
- temporal difference learning