However,evenwhentheprior is useful for generalization, distilling it to RL agent often interferes with RL training and degenerates sample efficiency.

RL agents learn policies from experience.

Neural Information Processing Systems http://nips.cc/

Solving OPE is often the starting point in many RL applications. To tackle the problem of OPE, the idea of importance sampling (IS) corrects the mismatch in the distributions under the behavior policy and target policy.

Our framework has three stages: instage 1,we leverage non-RL datasets (e.g. ImageNet) to learn task-agnostic visual representations; in stage 2, we use offline RL data (e.g. a limited number of expert demonstrations) to convert the task-agnostic representations intomorepowerfultask-specific representations; in stage 3, we fine-tune the agent with online RL.

Neural Information Processing Systems http://nips.cc/

RL that utilize function approximation to generalize observational data to unknown states/actions. The goal of this paper is to study the sample complexity of policy-based RL, which is arguably the simplest setting for RL with function approximation (Kearns et al., 1999; Kakade, 2003).