Strategically Conservative Q-Learning

6 June 2024

Yutaka Shimizu

Sergey Levine

Papers citing "Strategically Conservative Q-Learning"

3 / 3 papers shown

Title
Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning Mitsuhiko Nakamoto Yuexiang Zhai Anika Singh Max Sobol Mark Yi-An Ma Chelsea Finn Aviral Kumar Sergey Levine OffRL OnRL 109 108 0 09 Mar 2023
Offline Reinforcement Learning with Implicit Q-Learning Ilya Kostrikov Ashvin Nair Sergey Levine OffRL 206 832 0 12 Oct 2021
COMBO: Conservative Offline Model-Based Policy Optimization Tianhe Yu Aviral Kumar Rafael Rafailov Aravind Rajeswaran Sergey Levine Chelsea Finn OffRL 194 412 0 16 Feb 2021