Papers › POPO: Pessimistic Offline Policy Optimization

POPO: Pessimistic Offline Policy Optimization

26 Dec 2020arXiv:2012.13682archive 2025-07-28

Qiang He, Xinwen Hou

Offline reinforcement learning (RL), also known as batch RL, aims to optimize policy from a large pre-recorded dataset without interaction with the environment. This setting offers the promise of utilizing diverse, pre-collected datasets to obtain policies without costly, risky, active exploration. However, commonly used off-policy algorithms based on Q-learning or actor-critic perform poorly when learning from a static dataset. In this work, we study why off-policy RL methods fail to learn in offline setting from the value function view, and we propose a novel offline RL algorithm that we call Pessimistic Offline Policy Optimization (POPO), which learns a pessimistic value function to get a strong policy. We find that POPO performs surprisingly well and scales to tasks with high-dimensional state and action space, comparing or outperforming several state-of-the-art offline RL algorithms on benchmark tasks.

PaperPDFCode

Code

sweetice/POPO officialmentioned in paper report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Offline RLQ-LearningReinforcement Learning (RL)

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Q-Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections