Leveraging Offline Data in Online Reinforcement Learning. (arXiv:2211.04974v1 [cs.LG])

Two central paradigms have emerged in the reinforcement learning (RL)
community: online RL and offline RL. In the online RL setting, the agent has no
prior knowledge of the environment, and must interact with it in order to find
an $\epsilon$-optimal policy. In the offline RL setting, the learner instead
has access to a fixed dataset to learn from, but is unable to otherwise
interact with the environment, and must obtain the best policy it can from this
offline data. …

arxiv data offline online reinforcement learning reinforcement reinforcement learning