On Reducing Undesirable Behavior in Deep-Reinforcement-Learning-Based Software.
Ophir M. CarmelGuy KatzPublished in: Proc. ACM Softw. Eng. (2024)
Keyphrases
- reinforcement learning
- software systems
- software tools
- model free
- software architecture
- multi agent environments
- state space
- real robot
- reinforcement learning algorithms
- source code
- optimal policy
- software evolution
- markov decision processes
- software package
- temporal difference
- software maintenance
- behavior analysis
- software packages
- hardware design
- embedded systems
- software testing
- function approximation
- real time
- learning process
- user interface
- learning environment
- case study
- learning algorithm
- data mining
- data sets