Bounded robustness in reinforcement learning via lexicographic objectives.
Daniel Jarne OrniaLicio RomaoLewis HammondManuel Mazo Jr.Alessandro AbatePublished in: L4DC (2024)
Keyphrases
- reinforcement learning
- function approximation
- model free
- state space
- robotic control
- computational efficiency
- optimal policy
- machine learning
- multi agent
- learning process
- temporal difference
- data sets
- real time
- knowledge base
- transition model
- learning classifier systems
- multiple objectives
- optimal control
- neural network
- markov decision processes
- real world
- np complete
- learning algorithm
- mobile robot
- evolutionary algorithm