RL-Based Method for Benchmarking the Adversarial Resilience and Robustness of Deep Reinforcement Learning Policies.
Vahid BehzadanWilliam H. HsuPublished in: SAFECOMP Workshops (2019)
Keyphrases
- reinforcement learning
- optimal policy
- computational efficiency
- high accuracy
- preprocessing
- cost function
- dynamic programming
- multi agent
- significant improvement
- markov decision processes
- transfer learning
- clustering method
- detection method
- fitted q iteration
- genetic algorithm
- model free
- segmentation method
- supervised learning
- support vector machine
- state space
- probabilistic model
- pairwise