"One Policy is Enough: Parallel Exploration with a Single Policy is Minimax ..."

Pedro Cisneros-Velarde et al. (2022)

> Home

Details and statistics

DOI: 10.48550/ARXIV.2205.15891

access: open

type: Informal or Other Publication

metadata version: 2022-06-01

- view
  - electronic edition via DOI (open access)
  authority control:
- export record
  dblp key:
  - journals/corr/abs-2205-15891
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/journals/corr/abs-2205-15891
Pedro Cisneros-Velarde, Boxiang Lyu, Sanmi Koyejo, Mladen Kolar:
One Policy is Enough: Parallel Exploration with a Single Policy is Minimax Optimal for Reward-Free Reinforcement Learning. CoRR abs/2205.15891 (2022)

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.