Task-agnostic Exploration in Reinforcement Learning

Efficient exploration is one of the main challenges in reinforcement learning (RL). Most existing sample-efficient algorithms assume the existence of a single reward function during exploration. In many practical scenarios, however, there is not a single underlying reward function to guide the exploration, for instance, when an agent needs to learn many skills simultaneously, or multiple conflicting objectives need to be balanced. To address these challenges, we propose the $\mathit{\text{task-agnostic}}\mathit{\text{RL}}$ framework: In the exploration phase, the agent first collects trajectories by exploring the MDP without the guidance of a reward function. After exploration, it aims at finding near-optimal policies for $N$ tasks, given the collected trajectories augmented with $\mathit{\text{sampled}}\mathit{\text{rewards}}$ for each task. We present an efficient task-agnostic RL algorithm, $\text{textsc}UCBZero$, that finds $ϵ$-optimal policies for $N$ arbitrary tasks after at most $\tilde O(\log(N)H^5SA/\epsilon^2)$explorationepisodes\mathrm{.}Wealsoprovidean$\Omega(\log (N)H^2SA/\epsilon^2)$lowerbound,showingthatthe$\log$dependencyon$N$isunavoidable\mathrm{.}Furthermore,weprovidean$N$-independent sample complexity bound of $\text{textsc}UCBZero$ in the statistically easier setting when the ground truth reward functions are known.