Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses.
Thanh Xuan NguyenTung Minh LuuTri TonChang D. YooPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- optimal policy
- multi agent
- digital image watermarking
- image watermarking
- state space
- policy search
- markov decision process
- partially observable environments
- machine learning
- partially observable domains
- denial of service attacks
- markov decision problems
- function approximators
- function approximation
- dynamic programming
- real time
- partially observable
- policy iteration
- temporal difference
- model free
- control policies
- countermeasures
- policy gradient
- lightweight
- learning algorithm