Online Regret Bounds for Undiscounted Continuous Reinforcement Learning - Archive ouverte HAL Access content directly
Conference Papers Year : 2012

Online Regret Bounds for Undiscounted Continuous Reinforcement Learning

(1) , (2)
1
2
Daniil Ryabko
  • Function : Author
  • PersonId : 848126
Not file

Dates and versions

hal-00765441 , version 1 (14-12-2012)

Identifiers

  • HAL Id : hal-00765441 , version 1

Cite

Ronald Ortner, Daniil Ryabko. Online Regret Bounds for Undiscounted Continuous Reinforcement Learning. NIPS 2012, 2012, Lake Tahoe, United States. pp.1772--1780. ⟨hal-00765441⟩
6799 View
0 Download

Share

Gmail Facebook Twitter LinkedIn More