Reward Attack on Stochastic Bandits with Non-Stationary Rewards.
Chenye YangGuanlin LiuLifeng LaiPublished in: ACSSC (2023)
Keyphrases
- non stationary
- multi armed bandits
- bandit problems
- multi armed bandit
- reinforcement learning
- fractional brownian motion
- markov processes
- stochastic systems
- reward function
- decision problems
- multi armed bandit problems
- adaptive algorithms
- markov decision processes
- empirical mode decomposition
- temporal evolution
- random fields
- expected reward
- change point detection
- autoregressive
- biomedical signals
- financial time series
- average reward
- control policy
- regret bounds
- total reward
- optimal policy
- computer vision