Reinforcement Learning
Explainable Reinforcement Learning via Model Transforms Mira Finkelstein
Understanding emerging behaviors of reinforcement learning (RL) agents may be difficult since such agents are often trained in complex environments using highly complex decision making procedures.
Near-Optimal Goal-Oriented Reinforcement Learning in Non-Stationary Environments
These algorithms combine the ideas of finite-horizon approximation [Chen et al., 2022a], special Bernstein-style bonuses of the MVP algorithm [Zhang et al., 2020], adaptive confidence widening [Wei and Luo, 2021], as
Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers
The widely adopted state-of-the-art Online Decision Transformer (ODT) still struggles when pretrained with low-reward offline data.
Near-Optimal Regret for Adversarial MDP with Delayed Bandit Feedback
The standard assumption in reinforcement learning (RL) is that agents observe feedback for their actions immediately.
