On Practical Robust Reinforcement Learning: Practical Uncertainty Set and Double-Agent Algorithm.
Ukjo HwangSongnam HongPublished in: CoRR (2023)
Keyphrases
- learning algorithm
- reinforcement learning
- multi agent
- matching algorithm
- computationally efficient
- experimental evaluation
- dynamic programming
- computationally demanding
- detection algorithm
- optimization algorithm
- computational cost
- real world
- model free
- times faster
- decision making
- computational complexity
- multi agent systems
- cost function
- optimal solution
- worst case
- high accuracy
- preprocessing
- parameter tuning
- objective function
- recognition algorithm
- intelligent agents
- state abstraction
- neural network
- multiagent systems
- particle swarm optimization
- search space
- significant improvement