Reinforcement Learning
OfflineReinforcementLearningwithDifferential Privacy
Since offline RL does not require access to the environment, it can be applied to problems where interaction with environment is infeasible,e.g., when collecting new data is costly (trade or finance [Zhang et al., 2020]), risky (autonomous driving [Sallab et al., 2017]) or illegal / unethical (healthcare [Raghu etal.,2017]).
c056d6cf7b7108418f2b8c307dfaab02-Paper-Conference.pdf
Further, we are interested in algorithms that enjoy sample efficiency while leveraging (value) function approximation.
bf89c9fcd0ef605571a03666f6a6a44d-Paper-Conference.pdf
Furthermore, the theoretical guarantees of the transitivity and aggregation error bound are justified.
Dynamic Regret of Adversarial Linear Mixture MDPs
We study reinforcement learning in episodic inhomogeneous MDPs with adversarial full-information rewards and the unknown transition kernel. We consider the linear mixture MDPs whose transition kernel is a linear mixture model and choose the dynamic regret as the performance measure.
The Value of Reward Lookahead in Reinforcement Learning
In reinforcement learning (RL), agents sequentially interact with changing environments while aiming to maximize the obtained rewards.
Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL Y ang Yue
We also give unique insights into its effectiveness.
