Task-agnostic Exploration in Reinforcement Learning

Abstract

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 \textit{task-agnostic 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 \textit{sampled rewards} for each task. We present an efficient task-agnostic RL algorithm, \textsc{UCBZero}, that finds $\epsilon$-optimal policies for $N$ arbitrary tasks after at most $\tilde{O}(\log (N)H^{5}SA/{\epsilon }^2)$ exploration episodes. We also provide an $\Omega (\log (N)H^{2}SA/{\epsilon }^2)$ lower bound, showing that the $\log$ dependency on $N$ is unavoidable. Furthermore, we provide an $N$-independent sample complexity bound of \textsc{UCBZero} in the statistically easier setting when the ground truth reward functions are known.

References in corpus (8)

• Learning by Playing - Solving Sparse Reward Tasks from Scratch
• Go-Explore: a New Approach for Hard-Exploration Problems
• Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning
• Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds
• Almost Optimal Model-Free Reinforcement Learning via Reference-Advantage Decomposition
• Few-Shot Goal Inference for Visuomotor Learning and Planning
• Reward-Free Exploration for Reinforcement Learning
• Policy Certificates: Towards Accountable Reinforcement Learning

Cited by in corpus (8)

• Fast active learning for pure exploration in reinforcement learning
• Adaptive Reward-Free Exploration
• Nearly Minimax Optimal Reward-free Reinforcement Learning
• Accommodating Picky Customers: Regret Bound and Exploration Complexity for Multi-Objective Reinforcement Learning
• A Sharp Analysis of Model-based Reinforcement Learning with Self-Play
• A Simple Reward-free Approach to Constrained Reinforcement Learning
• Gap-Dependent Unsupervised Exploration for Reinforcement Learning
• Near-Optimal Reward-Free Exploration for Linear Mixture MDPs with Plug-in Solver