Temporaldifference(TD)learning algorithm is one of the most popular policy evaluation approaches.

In reinforcement learning, robust policies for high-stakes decision-making problems with limited data are usually computed by optimizing the percentile criterion .

Wemodel theeventofinterest asaspecial terminal state, andwe seek to estimate the survival distribution (i.e., the distribution of the hitting time for that terminal state) from anyother state.

Natural language-conditioned reinforcement learning (RL) enables agents to follow human instructions.

Such diversity hampers knowledge sharing, learning, and generalization across tasks and environments.