Skip to Main content Skip to Navigation
Conference papers

Fast active learning for pure exploration in reinforcement learning

Abstract : Realistic environments often provide agents with very limited feedback. When the environment is initially unknown, the feedback, in the beginning, can be completely absent, and the agents may first choose to devote all their effort on exploring efficiently. The exploration remains a challenge while it has been addressed with many hand-tuned heuristics with different levels of generality on one side, and a few theoretically backed exploration strategies on the other. Many of them are incarnated by intrinsic motivation and in particular explorations bonuses. A common rule of thumb for exploration bonuses is to use 1/ √ n bonus that is added to the empirical estimates of the reward, where $n$ is a number of times this particular state (or a state-action pair) was visited. We show that, surprisingly, for a pure-exploration objective of reward-free exploration, bonuses that scale with 1/n bring faster learning rates, improving the known upper bounds with respect to the dependence on the horizon $H$. Furthermore, we show that with an improved analysis of the stopping time, we can improve by a factor $H$ the sample complexity in the best-policy identification setting, which is another pure-exploration objective, where the environment provides rewards but the agent is not penalized for its behavior during the exploration phase.
Document type :
Conference papers
Complete list of metadata

https://hal.inria.fr/hal-02906985
Contributor : Michal Valko Connect in order to contact the contributor
Submitted on : Friday, July 16, 2021 - 4:11:56 PM
Last modification on : Tuesday, June 14, 2022 - 11:58:48 AM

File

menard2021fast.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02906985, version 3

Collections

Citation

Pierre Ménard, Omar Darwiche Domingues, Emilie Kaufmann, Anders Jonsson, Edouard Leurent, et al.. Fast active learning for pure exploration in reinforcement learning. International Conference on Machine Learning, Jul 2021, Vienna, Austria. ⟨hal-02906985v3⟩

Share

Metrics

Record views

215

Files downloads

182