Can I read Model-Free Active Exploration in Reinforcement Learning on EtoBox?

Model-Free Active Exploration in Reinforcement Learning by Russo, Alessio; Proutiere, Alexandre is a scholarly article available to read on EtoBox.

What is Model-Free Active Exploration in Reinforcement Learning about?

We study the problem of exploration in Reinforcement Learning and present a novel model-free solution. We adopt an information-theoretical viewpoint and start from the instance-specific lower bound of the number of samples that have to be collected to identify a nearly-optimal policy. Deriving this lower bound along with the optimal exploration strategy entails solving an intricate optimization problem and requires a model of the system. In turn, most existing sample optimal exploration algorithms rely on estimating the model. We derive an approximation of the instance-specific lower bound that only involves quantities that can be inferred using model-free approaches. Leveraging this approximation, we devise an ensemble-based model-free exploration strategy applicable to both tabular and continuous Markov decision processes. Numerical results demonstrate that our strategy is able to identify efficient policies faster than state-of-the-art exploration approaches

Author

Russo, Alessio; Proutiere, Alexandre

Published

2024

Language

EN