A Provably Efficient Sample Collection Strategy for Reinforcement Learning

Abstract

One of the challenges in online reinforcement learning (RL) is that the agent needs to trade off the exploration of the environment and the exploitation of the samples to optimize its behavior. Whether we optimize for regret, sample complexity, state-space coverage or model estimation, we need to strike a different exploration-exploitation trade-off. In this paper, we propose to tackle the exploration-exploitation problem following a decoupled approach composed of: 1) An "objective-specific" algorithm that (adaptively) prescribes how many samples to collect at which states, as if it has access to a generative model (i.e., a simulator of the environment); 2) An "objective-agnostic" sample collection exploration strategy responsible for generating the prescribed samples as fast as possible. Building on recent methods for exploration in the stochastic shortest path problem, we first provide an algorithm that, given as input the number of samples $b(s,a)$ needed in each state-action pair, requires $\tilde{O}(BD+D^{3/2}{S}^{2}A)$ time steps to collect the $B={\sum }_{s,a}b(s,a)$ desired samples, in any unknown communicating MDP with $S$ states, $A$ actions and diameter $D$. Then we show how this general-purpose exploration algorithm can be paired with "objective-specific" strategies that prescribe the sample requirements to tackle a variety of settings -- e.g., model estimation, sparse reward discovery, goal-free cost-free exploration in communicating MDPs -- for which we obtain improved or novel sample complexity guarantees.

NeurIPS 2021

References in corpus (15)

• REGAL: A Regularization based Algorithm for Reinforcement Learning in Weakly Communicating MDPs
• Provably Efficient Maximum Entropy Exploration
• Conservative Contextual Linear Bandits
• Almost Optimal Model-Free Reinforcement Learning via Reference-Advantage Decomposition
• Stochastic Primal-Dual Methods and Sample Complexity of Reinforcement Learning
• Primal-Dual $\pi$ Learning: Sample Complexity and Sublinear Run Time for Ergodic Markov Decision Problems
• Fast active learning for pure exploration in reinforcement learning
• Reward-Free Exploration for Reinforcement Learning
• Active Exploration in Markov Decision Processes
• Exploration-Exploitation Trade-off in Reinforcement Learning on Online Markov Decision Processes with Global Concave Rewards
• Improved Analysis of UCRL2 with Empirical Bernstein Inequality
• Nearly Minimax Optimal Reward-free Reinforcement Learning
• Improved Sample Complexity for Incremental Autonomous Exploration in MDPs
• Sample Complexity Bounds for Stochastic Shortest Path with a Generative Model
• Regret Bounds for Stochastic Shortest Path Problems with Linear Function Approximation

Cited by in corpus (1)

• Finding the Stochastic Shortest Path with Low Regret: The Adversarial Cost and Unknown Transition Case