Projected Off-Policy Q-Learning (POP-QL) for Stabilizing Offline
Reinforcement Learning

Projected Off-Policy Q-Learning (POP-QL) for Stabilizing Offline Reinforcement Learning

25 November 2023

Melrose Roderick

Felix Berkenkamp

J. Zico Kolter

Papers citing "Projected Off-Policy Q-Learning (POP-QL) for Stabilizing Offline Reinforcement Learning"

Title
No papers