AutoCost: Evolving Intrinsic Cost for Zero-violation Reinforcement Learning.
Tairan HeWeiye ZhaoChangliu LiuPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- function approximation
- high cost
- constraint violations
- multi agent
- reinforcement learning algorithms
- total cost
- learning algorithm
- markov decision process
- model free
- multi class
- neural network
- cost reduction
- cost savings
- average cost
- multi agent reinforcement learning
- data sets
- robotic control
- temporal difference
- action selection
- dynamic programming
- search space
- objective function
- decision trees
- genetic algorithm
- machine learning
- databases