In recent years, domains such as natural language processing and image
r...
We consider how to most efficiently leverage teleoperator time to collec...
Most theoretically motivated work in the offline reinforcement learning
...
Several recent works have proposed a class of algorithms for the offline...
Recent progress in deep learning has relied on access to large and diver...
We introduce quantile filtered imitation learning (QFIL), a novel policy...
Most prior approaches to offline reinforcement learning (RL) have taken ...
We consider the problem of evaluating representations of data for use in...
We consider the task of policy learning from an offline dataset generate...
We consider the exploration-exploitation dilemma in finite-horizon
reinf...
While there are convergence guarantees for temporal difference (TD) lear...