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.

In real-world decision-making tasks, learning an optimal policy without a trialand-error process is an appealing challenge. When expert demonstrations are available, imitation learning that mimics expert actions can learn a good policy efficiently.

A fundamental question in the theory of reinforcement learning is: suppose the optimalQ-function lies inthe linear span ofagivenddimensional feature mapping, is sample-efficient reinforcement learning (RL) possible? The recent and remarkable result of Weisz et al. (2020) resolves this question in the negative, providinganexponential(ind)samplesizelowerbound,whichholdsevenifthe agent has access to a generative model of the environment. One may hope that such a lower can be circumvented with an even stronger assumption that there isaconstant gapbetween the optimalQ-value ofthe best action and that ofthe second-best action (for allstates); indeed, the construction inWeisz etal.